ICML 2021 Accepted Papers 1183

If you are an author on a paper here and your institution is missing, you should immediately update your CMT profile and the corresponding profile at https://ICML.cc/EditProfile. Use your browser's search (ctrl+f or cmd+f) to find your papers.

Please read this guide on how to design for color blindness for tips to make your poster friendlier to the color-blind.


The Heavy-Tail Phenomenon in SGD
Mert Gurbuzbalaban (Rutgers University) · Umut Simsekli (Inria/ENS) · Lingjiong Zhu (Florida State University)

Asymmetric Heavy Tails and Implicit Bias in Gaussian Noise Injections
Alexander D Camuto (University of Oxford) · Xiaoyu Wang (Florida State University) · Lingjiong Zhu (Florida State University) · Christopher Holmes (University of Oxford) · Mert Gurbuzbalaban (Rutgers University) · Umut Simsekli (Inria/ENS)

Relative Positional Encoding for Transformers with Linear Complexity
Antoine Liutkus (Inria) · Ondřej Cífka (Télécom Paris, Institut Polytechnique de Paris) · Shih-Lun Wu (National Taiwan University) · Umut Simsekli (Inria/ENS) · Yi-Hsuan Yang (Academia Sinica) · Gaël RICHARD (Télécom Paris)

Isometric Gaussian Process Latent Variable Model for Dissimilarity Data
Martin Jørgensen (University of Oxford) · Søren Hauberg (Technical University of Denmark)

KD3A: Unsupervised Multi-Source Decentralized Domain Adaptation via Knowledge Distillation
Haozhe Feng (State Key Lab of CAD&CG, Zhejiang University) · Zhaoyang You (Zhejiang University) · Minghao Chen (Zhejiang University) · Tianye Zhang (Zhejiang University) · Minfeng Zhu (State Key Lab of CAD&CG, Zhejiang University) · Fei Wu (Zhejiang University, China) · Chao Wu (Zhejiang University) · Wei Chen (State Key Lab of CAD&CG, Zhejiang University)

Debiasing a First-order Heuristic for Approximate Bi-level Optimization
Valerii Likhosherstov (University of Cambridge) · Xingyou Song (Google Brain) · Krzysztof Choromanski (Google Brain Robotics) · Jared Quincy Davis (DeepMind & Stanford University) · Adrian Weller (University of Cambridge, Alan Turing Institute)

Outside the Echo Chamber: Optimizing the Performative Risk
John Miller (University of California, Berkeley) · Juan Perdomo (University of California, Berkeley) · Tijana Zrnic (University of California, Berkeley)

Two Heads are Better Than One: Hypergraph-Enhanced Graph Reasoning for Visual Event Ratiocination
Wenbo Zheng (School of Software Engineering, Xi'an Jiaotong University) · Lan Yan (The State Key Laboratory for Management and Control of Complex Systems, Institute of Automation, Chinese Academy of Sciences) · Chao Gou (School of Intelligent Systems Engineering, Sun Yat-sen University) · Fei-Yue Wang (The State Key Laboratory for Management and Control of Complex Systems, Institute of Automation, Chinese Academy of Sciences)

Riemannian Convex Potential Flows
samuel cohen (University College London) · Brandon Amos (Facebook AI Research) · Yaron Lipman (Facebook AI Research)

Catformer: Designing Stable Transformers via Sensitivity Analysis
Jared Quincy Davis (DeepMind & Stanford University) · Albert Gu (Stanford University) · Tri Dao (Stanford) · Krzysztof Choromanski (Google Brain Robotics) · Christopher Re (Stanford) · Percy Liang (Stanford University) · Chelsea Finn (Google)

MOTS: Minimax Optimal Thompson Sampling
Tianyuan Jin (National University of Singapore) · Pan Xu (California Institute of Technology) · Jieming Shi (The Hong Kong Polytechnic University) · Xiaokui Xiao (National University of Singapore) · Quanquan Gu (University of California, Los Angeles)

On the Power of Localized Perceptron for Label-Optimal Learning of Halfspaces with Adversarial Noise
Jie Shen (Stevens Institute of Technology)

Towards Accurate Spiking Neural Networks Conversion by Adaptive Threshold and Layer-wise Calibration
Yuhang Li (Yale University) · Shikuang Deng (University of Electronic Science and Technology of China) · Xin Dong (Harvard University) · Ruihao Gong (SenseTime) · Shi Gu (UESTC)

Unified Robust Semi-Supervised Variational Autoencoder
Xu Chen (SAS Inc)

Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Loss
Xue Yang (Shanghai Jiao Tong University) · Junchi Yan (Shanghai Jiao Tong University) · Qi Ming (School of Automation, Beijing Institute of Technology) · Wentao Wang (Shanghai Jiao Tong University) · xiaopeng zhang (Huawei Cloud EI ) · Qi Tian (Huawei Cloud & AI)

Agnostic Microfoundations for Strategic Classification
Meena Jagadeesan (UC Berkeley) · Celestine Mendler-Dünner (University of California, Berkeley) · University of California Moritz Hardt (University of California, Berkeley)

Efficient Differentiable Simulation of Articulated Bodies
Yi-Ling Qiao (University of Maryland, College Park) · Junbang Liang (University of Maryland, College Park) · Vladlen Koltun (Intel Labs) · Ming Lin (UMD-CP & UNC-CH)

CATE: Computation-aware Neural Architecture Encoding with Transformers
Shen Yan (Michigan State University) · Kaiqiang Song (University of Central Florida) · Fei Liu (University of Central Florida) · Mi Zhang (Michigan State University)

Uncertainty Principles of Encoding GANs
Ruili Feng (USTC) · Zhouchen Lin (Peking University) · jiapeng zhu (Beijing Institute of Technology) · Deli Zhao (Alibaba Group) · Jingren Zhou (Alibaba Group) · Zheng-Jun Zha (University of Science and Technology of China)

Path Planning using Neural A* Search
Ryo Yonetani (OMRON SINIC X) · Tatsunori Taniai (OMRON SINIC X) · Mohammadamin Barekatain (DeepMind) · Mai Nishimura (OMRON SINIC X) · Asako Kanezaki (Tokyo Institute of Technology)

Backpropagated Neighborhood Aggregation for Accurate Training of Spiking Neural Networks
Yukun Yang (University of California, Santa Barbara) · Wenrui Zhang (University of California, Santa Barbara) · Peng Li (University of California at Santa Barbara)

Voice2Series: Reprogramming Acoustic Models for Time Series Classification
Huck Yang (Georgia Tech) · Yun-Yun Tsai (Columbia University) · Pin-Yu Chen (IBM Research AI)

Accumulated Decoupled Learning with Gradient Staleness Mitigation for Convolutional Neural Networks
Huiping Zhuang (Nanyang Technological Univerisity) · Zhenyu Weng (Nanyang Technological University) · Fulin Luo (Nanyang Technological University) · Kar-Ann Toh (Yonsei University) · Haizhou Li (National University of Singapore) · Zhiping Lin (Nanyang Technological University)

Model Fusion for Personalized Learning
Thanh Lam (National University of Singapore) · Nghia Hoang (AWS AI Labs, Amazon) · Bryan Kian Hsiang Low (National University of Singapore) · Patrick Jaillet (MIT)

A statistical perspective on distillation
Aditya Menon (Google Research) · Ankit Singh Rawat (Google) · Sashank Jakkam Reddi (Google) · Seungyeon Kim (Google Research) · Sanjiv Kumar (Google Research, NY)

NeRF-VAE: A Geometry Aware 3D Scene Generative Model
Adam Kosiorek (DeepMind) · Heiko Strathmann (Deepmind) · Daniel Zoran (DeepMind) · Pol Moreno (Google DeepMind) · Rosalia Schneider (DeepMind) · Sona Mokra (Deepmind) · Danilo J. Rezende (DeepMind)

Revisiting Rainbow: Promoting more insightful and inclusive deep reinforcement learning research
Johan Obando Ceron (UAO) · Pablo Samuel Castro (Google Brain)

Learning Representations by Humans, for Humans
Anna Hilgard (Harvard University) · Nir Rosenfeld (Harvard) · Mahzarin Banaji (Harvard University) · Jack Cao (Harvard) · David Parkes (Harvard University)

Instance Specific Approximations for Submodular Maximization
Eric Balkanski (Columbia University) · Sharon Qian (Harvard) · Yaron Singer (Harvard)

Learning Bounds for Open-Set Learning
Zhen Fang (University of Technology Sydney) · Jie Lu (University of Technology Sydney) · Anjin Liu (University of Technology Sydney) · Feng Liu (University of Technology Sydney) · Guangquan Zhang (University of Technology Sydney)

Batch Value-function Approximation with Only Realizability
Tengyang Xie (University of Illinois at Urbana-Champaign) · Nan Jiang (University of Illinois at Urbana-Champaign)

Accelerate CNNs from Three Dimensions: A Comprehensive Pruning Framework
Wenxiao Wang (ZJU) · Minghao Chen (Zhejiang University) · Shuai Zhao (The Chinese University of HongKong, Shenzhen) · Long Chen (Columbia University) · Jinming Hu (Microsoft) · Haifeng Liu (ZJU) · Deng Cai (ZJU) · Xiaofei He (Zhejiang University) · Wei Liu (Tencent AI Lab)

Consistent Nonparametric Methods for Network Assisted Covariate Estimation
Xueyu Mao (University of Texas at Austin) · Deepayan Chakrabarti (University of Texas, Austin) · Purnamrita Sarkar (UT Austin)

Neural-Pull: Learning Signed Distance Function from Point clouds by Learning to Pull Space onto Surface
Baorui Ma (Tsinghua university) · Zhizhong Han (Wayne State University) · Yushen Liu (Tsinghua University) · Matthias Zwicker (University of Maryland)

How could Neural Networks understand Programs?
Dinglan Peng (University of Science and Technology of China) · Shuxin Zheng (Microsoft Research) · Yatao Li (Microsoft Research Asia) · Guolin Ke (MSRA) · Di He (Microsoft Research) · Tie-Yan Liu (Microsoft)

Message Passing Adaptive Resonance Theory for Online Active Semi-supervised Learning
Taehyeong Kim (LG Electronics) · Injune Hwang (Seoul National University) · Hyundo Lee (Seoul National University) · Hyunseo Kim (Seoul National University) · Won-Seok Choi (Seoul National University) · Joseph Lim (Univ. of Southern California) · Byoung-Tak Zhang (Seoul National Univserity)

Improving Generalization in Meta-learning via Task Augmentation
Huaxiu Yao (Stanford University) · Long-Kai Huang (Tencent AI Lab) · Linjun Zhang (Rutgers University) · Ying WEI (City University of Hong Kong) · Li Tian (Tencent ) · James Zou (Stanford University) · Junzhou Huang (University of Texas at Arlington / Tencent AI Lab) · Zhenhui (Jessie) Li (Penn State University)

Autoencoding Under Normalization Constraints
Sangwoong Yoon (Seoul National University) · Yung-Kyun Noh (Seoul National University) · Frank Chongwoo Park (Seoul National University)

Sample-Optimal PAC Learning of Halfspaces with Malicious Noise
Jie Shen (Stevens Institute of Technology)

Strategic Classification in the Dark
Ganesh Ghalme (Technion- Israel Institute of Technolgy, Haifa) · Vineet Nair (Technion) · Itay Eilat (Technion) · Inbal Talgam-Cohen (Technion) · Nir Rosenfeld (Harvard)

Revisiting Point Cloud Classification with a Simple and Effective Baseline
Ankit Goyal (Princeton University) · Hei Law (Princeton University) · Bowei Liu (Princeton University) · Alejandro Newell (Princeton University) · Jia Deng (Princeton University)

Differentiable Spatial Planning using Transformers
Devendra Singh Chaplot (Carnegie Mellon University) · Deepak Pathak (CMU, FAIR) · Jitendra Malik (University of California at Berkeley)

Near-Optimal Entrywise Anomaly Detection for Low-Rank Matrices with Sub-Exponential Noise
Vivek Farias (MIT) · Andrew Li (Carnegie Mellon University) · Tianyi Peng (MIT)

Explaining Time Series Predictions with Dynamic Masks
Jonathan Crabbé (University of Cambridge) · Mihaela van der Schaar (University of Cambridge and UCLA)

Bayesian Online Meta-Learning
Pauching Yap (University College London) · Hippolyt Ritter (University College London) · David Barber (University College London)

BASGD: Buffered Asynchronous SGD for Byzantine Learning
Yi-Rui Yang (Nanjing University) · Wu-Jun Li (Nanjing University)

Near-Optimal Linear Regression under Distribution Shift
Qi Lei (Princeton University) · Wei Hu (Princeton University) · Jason Lee (Princeton)

iDARTS: Differentiable Architecture Search with Stochastic Implicit Gradients
Miao Zhang (Monash University / UTS) · Steven Su (University of Technology Sydney) · Shirui Pan (Monash University) · Xiaojun Chang (Monash University) · Ehsan Abbasnejad (University of Adelaide) · Reza Haffari (Monash University, Australia)

Multiscale Invertible Generative Networks for High-Dimensional Bayesian Inference
Shumao Zhang (California Institute of Technology) · Pengchuan Zhang (Microsoft Research AI) · Thomas Hou (California Institute of Technology)

Differentiable Dynamic Quantization with Mixed Precision and Adaptive Resolution
zhaoyang zhang (The Chinese University of Hong Kong) · Wenqi Shao (The Chinese University of HongKong) · Jinwei Gu (Sensebrain) · Xiaogang Wang (Chinese University of Hong Kong, Hong Kong) · Ping Luo (The University of Hong Kong)

Crystallization Learning with the Delaunay Triangulation
Jiaqi Gu (The University of Hong Kong) · Guosheng Yin (University of Hong Kong)

Principled Exploration via Optimistic Bootstrapping and Backward Induction
Chenjia Bai (Harbin Institute of Technology) · Lingxiao Wang (Northwestern University) · Lei Han (Tencent AI Lab) · Jianye Hao (Tianjin University) · Animesh Garg (University of Toronto, Vector Institute, Nvidia) · Peng Liu (Harbin Institute of Technology) · Zhaoran Wang (Northwestern U)

Learning to Weight Imperfect Demonstrations
Yunke Wang (Wuhan University) · Chang Xu (University of Sydney) · Bo Du (Wuhan University) · Honglak Lee (Google / U. Michigan)

Deep Latent Graph Matching
Tianshu Yu (Arizona State University) · Runzhong Wang (Shanghai Jiao Tong University) · Junchi Yan (Shanghai Jiao Tong University) · baoxin Li (Arizona State University)

First-Order Methods for Wasserstein Distributionally Robust MDP
Julien Grand-Clement (IEOR Department, Columbia University) · Christian Kroer (Columbia University)

REPAINT: Knowledge Transfer in Deep Reinforcement Learning
Yunzhe Tao (ByteDance) · Sahika Genc (Amazon AI) · Jonathan Chung (AWS) · TAO SUN (Amazon.com) · Sunil Mallya (Amazon AWS)

Non-Exponentially Weighted Aggregation: Regret Bounds for Unbounded Loss Functions
Pierre Alquier (RIKEN)

Generalization Bounds in the Presence of Outliers: a Median-of-Means Study
Pierre Laforgue (University of Milan) · Guillaume Staerman (Télécom Paris) · Stephan Clémençon (Télécom Paris)

Differentially Private Quantiles
Jennifer Gillenwater (Google Research NYC) · Matthew Joseph (Google) · Alex Kulesza (Google)

SiameseXML: Siamese Networks meet Extreme Classifiers with 100M Labels
Kunal Dahiya (IIT Delhi) · Ananye Agarwal (IIT Delhi) · Deepak Saini (Microsoft Research India) · Gururaj K (Microsoft) · Jian Jiao (Microsoft) · Amit Singh (Microsoft) · Sumeet Agarwal (Indian Institute of Technology Delhi) · Purushottam Kar (IIT Kanpur) · Manik Varma (Microsoft Research)

EfficientNetV2: Smaller Models and Faster Training
Mingxing Tan (Google Brain) · Quoc Le (Google Brain)

Gradient Disaggregation: Breaking Privacy in Federated Learning by Reconstructing the User Participant Matrix
Maximilian Lam (Harvard) · Gu-Yeon Wei () · David Brooks (Harvard University) · Vijay Janapa Reddi (Harvard University) · Michael Mitzenmacher (Harvard)

Learning by Turning: Neural Architecture Aware Optimisation
Yang Liu (Abacus.AI) · Jeremy Bernstein (Caltech) · Markus Meister (Caltech) · Yisong Yue (Caltech)

On the Proof of Global Convergence of Gradient Descent for Deep ReLU Networks with Linear Widths
Quynh Nguyen (MPI-MIS)

Tight Bounds on the Smallest Eigenvalue of the Neural Tangent Kernel for Deep ReLU Networks
Quynh Nguyen (MPI-MIS) · Marco Mondelli (IST Austria) · Guido Montufar (UCLA)

FILTRA: Rethinking Steerable CNN by Filter Transform
Bo Li (JD) · Qili Wang (JD Digits) · Gim Hee Lee (National University of Singapore)

Strategic Classification Made Practical
Sagi Levanon (Technion) · Nir Rosenfeld (Harvard)

Understanding Noise Injection in GANs
Ruili Feng (USTC) · Deli Zhao (Alibaba Group) · Zheng-Jun Zha (University of Science and Technology of China)

Variance Reduction via Primal-Dual Accelerated Dual Averaging for Nonsmooth Convex Finite-Sums
Chaobing Song (University of Wisconsin-Madison) · Stephen Wright (University of Wisconsin-Madison) · Jelena Diakonikolas (University of Wisconsin-Madison)

What Makes for End-to-End Object Detection?
Peize Sun (The University of Hong Kong) · Yi Jiang (Bytedance) · Enze Xie (The University of Hong Kong) · Wenqi Shao (The Chinese University of HongKong) · Zehuan Yuan (Bytedance.Inc) · Changhu Wang (ByteDance AI Lab) · Ping Luo (The University of Hong Kong)

Uncertainty Weighted Actor-Critic for Offline Reinforcement Learning
Yue Wu (Carnegie Mellon University) · Shuangfei Zhai (Apple) · Nitish Srivastava (Apple) · Joshua Susskind (Apple, Inc.) · Jian Zhang (Apple Inc.) · Ruslan Salakhutdinov (Carnegie Mellen University) · Hanlin Goh (Apple)

Event Outlier Detection in Continuous Time
Siqi Liu (University of Pittsburgh) · Milos Hauskrecht (University of Pittsburgh)

On Explainability of Graph Neural Networks via Subgraph Explorations
Hao Yuan (Texas A&M University) · Haiyang Yu (Texas A&M University) · Jie Wang (University of Science and Technology of China) · Kang Li (Rutgers) · Shuiwang Ji (Texas A&M University)

Optimal Sample Complexity for Compressed Sensing with Approximate Generative Priors
Ajil Jalal (University of Texas at Austin) · Sushrut Karmalkar (University of Texas at Austin) · Alexandros Dimakis (UT Austin) · Eric Price (UT-Austin)

Fairness for Image Generation with Uncertain Sensitive Attributes
Ajil Jalal (University of Texas at Austin) · Sushrut Karmalkar (University of Texas at Austin) · Jessica Hoffmann (University of Texas at Austin) · Alexandros Dimakis (UT Austin) · Eric Price (UT-Austin)

Quantitative Understanding of VAE as a Non-linearly Scaled Isometric Embedding
Akira Nakagawa (Fujitsu Limited) · Keizo Kato (Fujitsu Laboratories Ltd.) · Taiji Suzuki (The University of Tokyo / RIKEN)

Evolving Attention with Residual Convolutions
Yujing Wang (Peking University) · Yaming Yang (MSRA) · Jiangang Bai (Peking University) · Mingliang Zhang (Peking University) · Jing Bai (Microsoft) · JING YU (Institute of Information Engineering, Chinese Academy of Sciences) · Ce Zhang (ETH Zurich) · Gao Huang (Tsinghua) · Yunhai Tong (Peking University)

Detecting Rewards Deterioration in Episodic Reinforcement Learning
Ido Greenberg (Technion) · Shie Mannor (Technion)

Deep Data Flow Analysis
Chris Cummins (Facebook AI Research) · Zacharias Fisches (ETH Zurich) · Tal Ben-Nun (ETH Zurich) · Torsten Hoefler (ETH Zürich) · Hugh Leather (Facebook AI Research) · Michael O'Boyle (University of Edinburgh)

Selecting Data Augmentation for Simulating Interventions
Maximilian Ilse (University of Amsterdam) · Jakub Tomczak (Vrije Universiteit Amsterdam) · Patrick Forré (University of Amsterdam)

GRAND: Graph Neural Diffusion
Ben Chamberlain (Twitter) · Maria Gorinova (University of Edinburgh) · Michael Bronstein (Twitter) · Stefan Webb (Twitter) · James Rowbottom (Twitter) · Emanuele Rossi (Twitter)

Few-Shot Neural Architecture Search
Yiyang Zhao (Worcester Polytechnic Institute) · Linnan Wang (Brown University) · Yuandong Tian (Facebook AI Research) · Rodrigo Fonseca (Brown University) · Tian Guo (Worcester Polytechnic Institute)

Optimal Complexity in Decentralized Training
Yucheng Lu (Cornell University) · Christopher De Sa (Cornell)

Variance Reduction in Training Forecasting Models with Subgroup Sampling
Yucheng Lu (Cornell University) · Youngsuk Park (Amazon Research) · Lifan Chen (Amazon) · Yuyang Wang (AWS AI Labs) · Christopher De Sa (Cornell) · Dean Foster (Amazon)

On the price of explainability for some clustering problems
Eduardo Laber (PUC-RIO) · Lucas Murtinho (PUC-Rio)

Learning Curves for Analysis of Deep Networks
Derek Hoiem (University of Illinios at Urbana-Champaign) · Tanmay Gupta (Allen Institute for Artificial Intelligence) · Zhizhong Li (Amazon AWS) · Michal Shlapentokh-Rothman (University of Illinois at Urbana-Champaign)

Large Scale Private Learning via Low-rank Reparametrization
Da Yu (Sun Yat-sen University) · Huishuai Zhang (Microsoft) · Wei Chen (Microsoft Research) · Jian Yin (Sun Yat-Sen University) · Tie-Yan Liu (Microsoft Research Asia)

Towards Distraction-Robust Active Visual Tracking
Fangwei Zhong (Peking University) · Peng Sun (Tencent AI Lab) · Wenhan Luo (Tencent AI Lab) · Tingyun Yan (peking university) · Yizhou Wang (Peking University)

Commutative Lie Group VAE for Disentanglement Learning
Xinqi Zhu (University of Sydney) · Chang Xu (University of Sydney) · Dacheng Tao (The University of Sydney)

Fundamental Tradeoffs in Distributionally Adversarial Training
Mohammad Mehrabi (University of Southern California) · Adel Javanmard (University of Southern California (USC)) · Ryan A. Rossi (Adobe Research) · Anup Rao (Adobe Research) · Tung Mai (Adobe Research)

Winograd Algorithm for AdderNet
Wenshuo Li (Huawei) · Hanting Chen (Peking University) · Mingqiang Huang (Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences) · Xinghao Chen (Noah's Ark Lab, Huawei Technologies) · Chunjing Xu (Huawei Noah's Ark Lab) · Yunhe Wang (Noah's Ark Lab, Huawei Technologies.)

Latent Space Symbol-Vector Coupling for Text Modeling
Bo Pang (University of California Los Angeles) · Ying Nian Wu (UCLA)

Radiance Fields from a Single Image
Konstantinos Rematas (Google) · Ricardo Martin-Brualla (Google) · Vittorio Ferrari (Google Research)

A Receptor Skeleton for Capsule Neural Networks
Jintai Chen (Zhejiang University) · Hongyun Yu (Zhejiang University) · Chengde Qian (Nankai University) · Danny Z Chen (University of Notre Dame) · Jian Wu (Zhejiang University)

What Does Rotation Prediction Tell Us about Classifier Accuracy under Varying Testing Environments?
Weijian Deng (Australian National University) · Liang Zheng (Australian National University) · Stephen Gould (Australian National University, Australia)

Adversarial Option-Aware Hierarchical Imitation Learning
Mingxuan Jing (Tsinghua University) · Wenbing Huang (Tsinghua University) · Fuchun Sun (Tsinghua) · Xiaojian Ma (University of California, Los Angeles) · Tao Kong (Bytedance) · Chuang Gan (MIT-IBM Watson AI Lab) · Lei Li (ByteDance AI Lab)

Autoregressive Denoising Diffusion Models for Multivariate Probabilistic Time Series Forecasting
Kashif Rasul (Zalando Research) · Calvin Seward (Zalando Research) · Ingmar Schuster (Zalando Research) · Roland Vollgraf (Zalando Research)

Model-Free Reinforcement Learning: from Clipped Pseudo-Regret to Sample Complexity
Zhang Zihan (Tsinghua University) · Yuan Zhou (UIUC) · Xiangyang Ji (Tsinghua University)

Asymmetric Loss Functions for Learning with Noisy Labels
Xiong Zhou (Harbin Institute of Technology) · Xianming Liu (Harbin Institute of Technology) · Junjun Jiang (Harbin Institute of Technology) · Xin Gao (Kaust) · Xiangyang Ji (Tsinghua University)

Near Optimal Reward-Free Reinforcement Learning
Zhang Zihan (Tsinghua University) · Simon Du (University of Washington) · Xiangyang Ji (Tsinghua University)

Dichotomous Optimistic Search to Quantify Human Perception
Julien Audiffren (Fribourg University)

Coded-InvNet for Resilient Prediction Serving Systems
Tuan Dinh (University of Wisconsin-Madison) · Kangwook Lee (UW Madison)

SoundDet: Polyphonic Moving Sound Event Detection and Localization from Raw Waveform
Yuhang He (University of Oxford) · Niki Trigoni (University of Oxford) · Andrew Markham (University of Oxford)

Non-Negative Bregman Divergence Minimization for Deep Direct Density Ratio Estimation
Masahiro Kato (Cyberagent) · Takeshi Teshima (The University of Tokyo / RIKEN)

Probabilistic Programs with Stochastic Conditioning
David Tolpin (Ben-Gurion University of the Negev) · Yuan Zhou (University of Oxford) · Tom Rainforth (University of Oxford) · Hongseok Yang (KAIST)

Dataset Condensation with Differentiable Siamese Augmentation
Bo Zhao (The University of Edinburgh) · Hakan Bilen (University of Edinburgh)

Communication-Efficient Distributed Optimization with Quantized Preconditioners
Foivos Alimisis (University of Geneva) · Peter Davies (IST Austria) · Dan Alistarh (IST Austria & NeuralMagic)

How Do Adam and Training Strategies Help BNNs Optimization
Zechun Liu (Carnegie Mellon University) · Zhiqiang Shen (Carnegie Mellon University) · Shichao Li (HKUST) · Koen Helwegen (Plumerai) · Dong Huang (Carnegie Mellon University) · Kwang-Ting Cheng (Hong Kong University of Science and Technology)

Self-Tuning for Data-Efficient Deep Learning
Ximei Wang (Tsinghua University) · Jinghan Gao (Tsinghua University) · Mingsheng Long (Tsinghua University) · Jianmin Wang (Tsinghua University)

On Reinforcement Learning with Adversarial Corruption and Its Application to Block MDP
Tianhao Wu (Peking University) · Yunchang Yang (Peking University) · Simon Du (University of Washington) · Liwei Wang (Peking University)

Optimization of Graph Neural Networks: Implicit Acceleration by Skip Connections and More Depth
Keyulu Xu (MIT) · Mozhi Zhang (University of Maryland) · Stefanie Jegelka (Massachusetts Institute of Technology) · Kenji Kawaguchi (MIT)

AdaXpert: Adapting Neural Architecture for Growing Data
Shuaicheng Niu (South China University of Technology) · Jiaxiang Wu (Tencent AI Lab) · Guanghui Xu (South China University of Technology) · Yifan Zhang (National University of Singapore) · Yong Guo (South China University of Technology) · Peilin Zhao (Tencent AI Lab) · Peng Wang (Northwestern Polytechnical University) · Mingkui Tan (South China University of Technology)

KO codes: inventing nonlinear encoding and decoding for reliable wireless communication via deep-learning
Ashok Vardhan Makkuva (UIUC) · Xiyang Liu (University of Washington) · Mohammad Vahid Jamali (University of Michigan) · Hessam Mahdavifar (University of Michigan) · Sewoong Oh (University of Washington) · Pramod Viswanath (UIUC)

Theory of Spectral Method for Union of Subspaces-Based Random Geometry Graph
Gen Li (Tsinghua University, China) · Yuantao Gu (Tsinghua University)

Re-understanding Finite-State Representations of Recurrent Policy Networks
Mohamad H Danesh (Oregon State University) · Anurag Koul (Oregon State University) · Alan Fern (Oregon State University) · Saeed Khorram (Oregon State University)

Towards Defending against Adversarial Examples via Attack-Invariant Features
Dawei Zhou (Xidian University) · Tongliang Liu (The University of Sydney) · Bo Han (HKBU / RIKEN) · Nannan Wang (Xidian University) · Chunlei Peng (Xidian University) · Xinbo Gao (Chongqing University of Posts and Telecommunications)

Asymptotic Normality and Confidence Intervals for Prediction Risk of the Min-Norm Least Squares Estimator
Zeng Li (Southern University of Science and Technology) · Chuanlong Xie (Huawei Noah's Ark Lab) · Qinwen Wang (Fudan University)

The Limits of Min-Max Optimization Algorithms: Convergence to Spurious Non-Critical Sets
Ya-Ping Hsieh (ETH) · Panayotis Mertikopoulos (CNRS and Criteo AI Lab) · Volkan Cevher (EPFL)

PixelTransformer: Sample Conditioned Signal Generation
Shubham Tulsiani (Facebook AI Research) · Abhinav Gupta (Carnegie Mellon University)

A Geometrical Approach to Learning Transferable Representation for Domain Adaptation Regression
Xinyang Chen (Tsinghua University) · Sinan Wang (Tsinghua University) · Mingsheng Long (Tsinghua University) · Jianmin Wang (Tsinghua University)

Inferring serial correlation with dynamic backgrounds
Song Wei (Georgia Tech) · Yao Xie (Georgia Institute of Technology) · Dobromir Rahnev (Georgia Tech)

Differentially Private Densest Subgraph Detection
Dung Nguyen (University of Virginia) · Anil Vullikanti (Biocomplexity Institute and Dept of Computer Science, University of Virginia)

Lower-Bounded Proper Losses for Weakly Supervised Classification
Shuhei M Yoshida (NEC / RIKEN) · Takashi Takenouchi (Future University Hakodate) · Masashi Sugiyama (RIKEN / The University of Tokyo)

Descending through a Crowded Valley - Benchmarking Deep Learning Optimizers
Robin M Schmidt (University of Tübingen) · Frank Schneider (University of Tübingen) · Philipp Hennig (University of Tübingen)

In-Database Regression in Input Sparsity Time
Rajesh Jayaram (Carnegie Mellon University) · Alireza Samadian (University of Pittsburgh) · David Woodruff (Carnegie Mellon University) · Peng Ye (Tsinghua University)

Adversarial Robustness Guarantees for Random Deep Neural Networks
Giacomo De Palma (Scuola Normale Superiore) · Bobak T Kiani (MIT) · Seth Lloyd (MIT)

Breaking the Deadly Triad with a Target Network
Shangtong Zhang (University of Oxford) · Hengshuai Yao (Huawei Technologies) · Shimon Whiteson (University of Oxford)

Average-Reward Off-Policy Policy Evaluation with Function Approximation
Shangtong Zhang (University of Oxford) · Yi Wan (University of Alberta) · Richard Sutton (DeepMind / Univ Alberta) · Shimon Whiteson (University of Oxford)

Quantifying and Reducing Bias in Maximum Likelihood Estimation of Structured Anomalies
Uthsav Chitra (Princeton University) · Kimberly Ding (Princeton University) · Jasper C.H. Lee (Brown University) · Benjamin Raphael (Princeton University)

AutoAttend: Automated Attention Representation Search
Chaoyu Guan (Tsinghua University) · Xin Wang (Tsinghua University) · wenwu zhu (Tsinghua University)

Communication-Efficient Distributed SVD via Local Power Iterations
Xiang Li (Peking University) · Shusen Wang (Stevens Institute of Technology) · Kun Chen (Peking University) · Zhihua Zhang (Peking University)

AutoSampling: Search for Effective Data Sampling Schedules
MING SUN (sensetime) · Haoxuan Dou (SenseTime Group Limited) · Baopu Li (BAIDU USA LLC) · Junjie Yan (Sensetime Group Limited) · Wanli Ouyang (The University of Sydney) · Lei Cui (Sensetime)

Variational (Gradient) Estimate of the Score Function in Energy-based Latent Variable Models
Fan Bao (Tsinghua University) · Kun Xu (Tsinghua University) · Chongxuan Li (Tsinghua University) · Lanqing Hong (Huawei) · Jun Zhu (Tsinghua University) · Bo Zhang (Tsinghua University)

SGLB: Stochastic Gradient Langevin Boosting
Aleksei Ustimenko (Yandex) · Liudmila Prokhorenkova (Yandex)

Object Segmentation Without Labels with Large-Scale Generative Models
Andrey Voynov (Yandex) · Stanislav Morozov (Yandex) · Artem Babenko (Yandex)

Regularized Submodular Maximization at Scale
Ehsan Kazemi (Google) · shervin minaee (Snap) · Moran Feldman (University of Haifa) · Amin Karbasi (Yale)

Training data-efficient image transformers & distillation through attention
Hugo Touvron (Facebook AI Research) · Matthieu Cord (Sorbonne University) · Douze Matthijs (Facebook AI Research) · Francisco Massa (Facebook AI Research) · Alexandre Sablayrolles (Facebook AI) · Herve Jegou (Facebook AI Research)

Align then Memorize: the dynamics of learning with feedback alignment
Maria Refinetti (Laboratoire de Physique de l’Ecole Normale Supérieure Paris) · Stéphane d'Ascoli (ENS / FAIR, Paris) · Ruben Ohana (Ecole Normale Supérieure & LightOn) · Sebastian Goldt (International School of Advanced Studies (SISSA))

Policy Analysis using Synthetic Controls in Continuous-Time
Alexis Bellot (University of Cambridge) · Mihaela van der Schaar (University of Cambridge and UCLA)

The Lipschitz Constant of Self-Attention
Hyunjik Kim (DeepMind) · George Papamakarios (DeepMind) · Andriy Mnih (DeepMind)

Large-Margin Contrastive Learning with Distance Polarization Regularizer
Shuo Chen (RIKEN) · Gang Niu (RIKEN) · Chen Gong (Nanjing University of Science and Technology) · Jun Li (Nanjing University of Science and Technology) · Jian Yang (Nanjing University of Science and Technology) · Masashi Sugiyama (RIKEN / The University of Tokyo)

Conditional Distributional Treatment Effect with Kernel Conditional Mean Embeddings and U-Statistic Regression
Junhyung Park (MPI for Intelligent Systems, Tübingen) · Uri Shalit (Technion) · Bernhard Schölkopf (MPI for Intelligent Systems Tübingen, Germany) · Krikamol Muandet (Max Planck Institute for Intelligent Systems)

Sawtooth Factorial Topic Embeddings Guided Gamma Belief Network
Zhibin Duan (Xidian University) · Dongsheng Wang (Xidian University) · Bo Chen (School of Electronic Engineering, Xidian University) · CHAOJIE WANG (XIDIAN UNIVERSITY) · Wenchao Chen (Xi'dian University) · yewen li (Xidian University) · Jie Ren (Xidian University) · Mingyuan Zhou (University of Texas at Austin)

Decentralized Riemannian Gradient Descent on the Stiefel Manifold
Shixiang Chen (Texas A&M University) · Alfredo Garcia (Texas A&M University) · Mingyi Hong (University of Minnesota) · Shahin Shahrampour (Texas A&M University)

LieTransformer: Equivariant Self-Attention for Lie Groups
Michael Hutchinson (University of Oxford) · Charline Le Lan (University of Oxford) · Sheheryar Zaidi (University of Oxford) · Emilien Dupont (University of Oxford) · Yee Whye Teh (Oxford and DeepMind) · Hyunjik Kim (DeepMind)

Beyond the Pareto Efficient Frontier: Constraint Active Search for Multiobjective Experimental Design
Gustavo Malkomes (SigOpt/Intel) · Bolong Cheng (SigOpt/Intel) · Eric Lee (SigOpt) · Michael McCourt (SigOpt)

Improved Confidence Bounds for the Linear Logistic Model and Applications to Bandits
Kwang-Sung Jun (University of Arizona) · Lalit Jain (University of Washington) · Houssam Nassif (amazon) · Blake Mason (University of Wisconsin, Madison)

Information Obfuscation of Graph Neural Networks
Peiyuan Liao (Carnegie Mellon University) · Han Zhao (University of Illinois at Urbana-Champaign) · Keyulu Xu (MIT) · Tommi Jaakkola (MIT) · Geoff Gordon (Carnegie Mellon University) · Stefanie Jegelka (Massachusetts Institute of Technology) · Ruslan Salakhutdinov (Carnegie Mellen University)

Boosting the Throughput and Accelerator Utilization of Specialized CNN Inference Beyond Increasing Batch Size
Jack Kosaian (Carnegie Mellon University) · Amar Phanishayee (Microsoft Research) · Matthai Philipose (Microsoft Research) · Debadeepta Dey (Microsoft) · Rashmi Vinayak (CMU)

Generative Causal Explanations for Graph Neural Networks
Wanyu Lin (Department of Computing, The Hong Kong Polytechnic University) · Hao Lan (University of Toronto) · Baochun Li (University of Toronto)

Adversarial Combinatorial Bandits with General Non-linear Reward Functions
Yanjun Han (Stanford University) · Yining Wang (Carnegie Mellon University) · Xi Chen (NYU)

Exponential Lower Bounds for Batch Reinforcement Learning: Batch RL can be Exponentially Harder than Online RL
Andrea Zanette (Stanford University)

DAGs with No Curl: An Efficient DAG Structure Learning Approach
Yue Yu (Lehigh University) · Tian Gao (IBM Research) · Naiyu Yin (Rensselaer Polytechnic Institute) · Qiang Ji (Renselaer Polytechnic Institute)

PAPRIKA: Private Online False Discovery Rate Control
Wanrong Zhang (Georgia Institute of Technology) · Gautam Kamath (University of Waterloo) · Rachel Cummings (Georgia Tech)

Near-Optimal Model-Free Reinforcement Learning in Non-Stationary Episodic MDPs
Weichao Mao (University of Illinois at Urbana-Champaign) · Kaiqing Zhang (University of Illinois at Urbana-Champaign/MIT) · Ruihao Zhu (MIT) · David Simchi-Levi (MIT) · Tamer Basar (University of Illinois at Urbana-Champaign)

Systematic Analysis of Cluster Similarity Indices: How to Validate Validation Measures
Martijn Gösgens (Eindhoven University of Technology) · Aleksei Tikhonov (Yandex) · Liudmila Prokhorenkova (Yandex)

When All We Need is a Piece of the Pie: A Generic Framework for Optimizing Two-way Partial AUC
Zhiyong Yang (IIE,CAS) · Qianqian Xu (Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences) · Shilong Bao (SKLOIS, Institute of Information Engineering, Chinese Academy of Sciences; SCS, University of CAS) · Yuan He (Alibaba Group) · Xiaochun Cao (Chinese Academy of Sciences) · Qingming Huang (University of Chinese Academy of Sciences)

Soft then Hard: Rethinking the Quantization in Neural Image Compression
Zongyu Guo (University of Science and Technology of China) · Zhizheng Zhang (University of Science and Technology of China) · Runsen Feng (University of Science and Technology of China) · Zhibo Chen (University of Science and Technology of China)

Learning Optimal Auctions with Correlated Valuations from Samples
CHUNXUE YANG (Nanyang Technological University) · Xiaohui Bei (Nanyang Technological University)

SMG: A Shuffling Gradient-Based Method with Momentum
Trang Tran (Cornell University) · Lam Nguyen (IBM Research, Thomas J. Watson Research Center) · Quoc Tran-Dinh (The University of North Carolina at Chapel Hill)

Differentiable Sorting Networks for Scalable Sorting and Ranking Supervision
Felix Petersen (University of Konstanz) · Christian Borgelt (University of Salzburg) · Hilde Kuehne (University of Frankfurt) · Oliver Deussen (University of Konstanz)

Necessary and sufficient conditions for causal feature selection in time series with latent common causes
Atalanti Mastakouri (Amazon Research Tuebingen) · Bernhard Schölkopf (MPI for Intelligent Systems Tübingen, Germany) · Dominik Janzing (Amazon)

HardCoRe-NAS: Hard Constrained diffeRentiable Neural Architecture Search
Niv Nayman (Alibaba Group) · Yonathan Aflalo (Alibaba) · Asaf Noy (Alibaba) · Lihi Zelnik (Alibaba)

DouZero: Mastering DouDizhu with Self-Play Deep Reinforcement Learning
Daochen Zha (Texas A&M University) · Jingru Xie (Kwai Inc.) · Wenye Ma (Kuaishou) · Sheng Zhang (Georgia Institute of Technology) · Xiangru Lian (Kwai Inc.) · Xia Hu (Texas A&M University) · Ji Liu (Kwai Seattle AI lab, University of Rochester)

A Sampling Based Method for Tensor Ring Decomposition
Osman Asif Malik (University of Colorado Boulder) · Stephen Becker (University of Colorado)

PAGE: A Simple and Optimal Probabilistic Gradient Estimator for Nonconvex Optimization
Zhize Li (King Abdullah University of Science and Technology (KAUST)) · Hongyan Bao (KAUST) · Xiangliang Zhang (KAUST) · Peter Richtarik (KAUST)

Accelerating Safe Reinforcement Learning with Constraint-mismatched Baseline Policies
Jimmy (Tsung-Yen) Yang (Princeton University) · Justinian Rosca (Siemens Corp.) · Karthik Narasimhan (Princeton) · Peter Ramadge (Princeton)

Revisiting Peng's Q($\lambda$) for Modern Reinforcement Learning
Tadashi Kozuno (University of Alberta) · Yunhao Tang (Columbia University) · Mark Rowland (DeepMind) · Remi Munos (DeepMind) · Steven Kapturowski (Deepmind) · Will Dabney (DeepMind) · Michal Valko (DeepMind / Inria / ENS Paris-Saclay) · David Abel (DeepMind)

Regularized Online Allocation Problems: Fairness and Beyond
Santiago Balseiro (Columbia University) · Haihao Lu (University of Chicago) · Vahab Mirrokni (Google Research)

Approximating a Distribution Using Weight Queries
Nadav Barak (Ben-Gurion University of the Negev) · Sivan Sabato (Ben-Gurion University of the Negev)

Ensemble Bootstrapping for Q-Learning
Oren Peer (Technion) · Chen Tessler (Technion) · Nadav Merlis (Technion) · Ron Meir (Technion Israeli Institute of Technology)

CLOCS: Contrastive Learning of Cardiac Signals Across Space, Time, and Patients
Dani Kiyasseh (University of Oxford) · Tingting Zhu (University of Oxford) · David Clifton (University of Oxford)

On the Random Conjugate Kernel and Neural Tangent Kernel
Zhengmian Hu (University of Pittsburgh) · Heng Huang (University of Pittsburgh & JD Finance America Corporation)

How Framelets Enhance Graph Neural Networks
Xuebin Zheng (The University of Sydney) · Bingxin Zhou (The University of Sydney) · Junbin Gao (The University of Sydney) · Yuguang Wang (Max Planck Institute for Mathematics in the Sciences; Shanghai Jiao Tong University; University of New South Wales) · Pietro Lió (University of Cambridge) · Ming Li (Zhejiang Normal University) · Guido Montufar (UCLA Math / Stat; MPI MIS)

Optimal Streaming Algorithms for Multi-Armed Bandits
Tianyuan Jin (National University of Singapore) · Keke Huang (National University of Singapore) · Jing Tang (The Hong Kong University of Science and Technology) · Xiaokui Xiao (National University of Singapore)

Near-Optimal Representation Learning for Linear Bandits and Linear RL
Xiaoyu Chen (Peking University) · Jiachen Hu (Peking University) · Chi Jin (Princeton University) · Lihong Li (Google Research) · Liwei Wang (Peking University)

Characterizing Fairness Over the Set of Good Models Under Selective Labels
Amanda Coston (Carnegie Mellon University) · Ashesh Rambachan (Harvard University) · Alexandra Chouldechova (CMU)

Measuring the Effectiveness of Dataset Manipulation Attacks
Avi Schwarzschild (University of Maryland) · Micah Goldblum (University of Maryland) · Arjun Gupta (University of Maryland College Park) · John P Dickerson (University of Maryland) · Tom Goldstein (University of Maryland)

Phasic Policy Gradient
Karl Cobbe (OpenAI) · Jacob Hilton (OpenAI) · Oleg Klimov (OpenAI) · John Schulman (OpenAI)

A Riemannian Block Coordinate Descent Method for Computing the Projection Robust Wasserstein Distance
Minhui Huang (UC Davis) · Shiqian Ma (UC Davis) · Lifeng Lai (UC Davis)

Projection Robust Wasserstein Barycenters
Minhui Huang (UC Davis) · Shiqian Ma (UC Davis) · Lifeng Lai (UC Davis)

Making Paper Reviewing Robust to Bid Manipulation Attacks
Ruihan Wu (Cornell University) · Chuan Guo (Facebook AI Research) · Felix Wu (Cornell University) · Rahul Kidambi (Amazon Search & AI) · Laurens van der Maaten (Facebook) · Kilian Weinberger (Cornell University)

Generalised Lipschitz Regularisation Equals Distributional Robustness
Zac Cranko (Universität Tübingen) · Zhan Shi (University of Illinois at Chicago) · Xinhua Zhang (University of Illinois at Chicago) · Richard Nock (Google Brain) · Simon Kornblith (Google Brain)

Disambiguation of Weak Supervision leading to Exponential Convergence rates
Vivien Cabannnes (INRIA) · Francis Bach (INRIA - Ecole Normale Supérieure) · Alessandro Rudi (INRIA, École Normale Supérieure)

Optimal Off-Policy Evaluation from Multiple Logging Policies
Nathan Kallus (Cornell University) · Yuta Saito (Tokyo Institute of Technology.) · Masatoshi Uehara (Cornell University)

FL-NTK: A Neural Tangent Kernel-based Framework for Federated Learning Analysis
Baihe Huang (Peking University) · Xiaoxiao Li (Yale University) · Zhao Song (UT-Austin & University of Washington) · Xin Yang (University of Washington)

Gaussian Process-Based Real-Time Learning for Safety Critical Applications
Armin Lederer (Technical University of Munich) · Alejandro Ordóñez Conejo (Tecnológico de Costa Rica) · Korbinian Maier (FRANKA EMIKA GmbH) · Wenxin Xiao (Peking University) · Jonas Umlauft (Technical University of Munich) · Sandra Hirche (Technical University of Munich)

Oblivious Sketching-based Central Path Method for Linear Programming
Zhao Song (UT-Austin & University of Washington) · Zheng Yu (Princeton University)

Risk Bounds and Rademacher Complexity in Batch Reinforcement Learning
Yaqi Duan (Princeton University) · Chi Jin (Princeton University) · Zhiyuan Li (Princeton University)

Clusterability as an Alternative to Anchor Points When Learning with Noisy Labels
Zhaowei Zhu (University of California, Santa Cruz) · Yiwen Song (Beijing University of Posts and Telecommunications) · Yang Liu (UC Santa Cruz)

Finite-Sample Analysis of Off-Policy Natural Actor-Critic Algorithm
sajad khodadadian (georgia institute of technology) · Zaiwei Chen (Georgia Institute of Technology) · Siva Maguluri (Georgia Tech)

Finding the Stochastic Shortest Path with Low Regret: the Adversarial Cost and Unknown Transition Case
Liyu Chen (USC) · Haipeng Luo (University of Southern California)

A Functional Perspective on Learning Symmetric Functions with Neural Networks
Aaron Zweig (New York University) · Joan Bruna (New York University)

Multiplying Matrices Without Multiplying
Davis Blalock (MIT, MosaicML) · John Guttag (MIT)

Accelerating Equilibrium Models by Stabilizing Their Jacobians
Shaojie Bai (Carnegie Mellon University) · Vladlen Koltun (Intel Labs) · Zico Kolter (Carnegie Mellon University / Bosch Center for AI)

Lenient Regret and Good-Action Identification in Gaussian Process Bandits
Xu Cai (National University of Singapore) · Selwyn Gomes (National University of Singapore) · Jonathan Scarlett (National University of Singapore)

On Lower Bounds for Standard and Robust Gaussian Process Bandit Optimization
Xu Cai (National University of Singapore) · Jonathan Scarlett (National University of Singapore)

SUNRISE: A Simple Unified Framework for Ensemble Learning in Deep Reinforcement Learning
Kimin Lee (UC Berkeley) · Michael Laskin (UC Berkeley) · Aravind Srinivas (UC Berkeley) · Pieter Abbeel (UC Berkeley & Covariant)

Resource Allocation in Multi-armed Bandit Exploration: Overcoming Sublinear Scaling with Adaptive Parallelism
Brijen Thananjeyan (UC Berkeley) · Kirthevasan Kandasamy (UC Berkeley) · Ion Stoica (UC Berkeley) · Michael Jordan (UC Berkeley) · Ken Goldberg (UC Berkeley) · Joseph E Gonzalez (UC Berkeley)

Supervised Tree-Wasserstein Distance
Yuki Takezawa (Kyoto University / RIKEN) · Ryoma Sato (Kyoto University) · Makoto Yamada (RIKEN AIP / Kyoto University)

CIFS: Improving Adversarial Robustness of CNNs via Channel-wise Importance-based Feature Selection
Hanshu YAN (NUS) · Jingfeng Zhang (RIKEN) · Gang Niu (RIKEN) · Jiashi Feng (National University of Singapore) · Vincent Tan (National University of Singapore) · Masashi Sugiyama (RIKEN / The University of Tokyo)

Noise and Fluctuation of Finite Learning Rate Stochastic Gradient Descent
Kangqiao Liu (University of Tokyo) · Liu Ziyin (University of Tokyo) · Masahito Ueda (University of Tokyo)

A Differentiable Point Process with Its Application to Spiking Neural Networks
Hiroshi Kajino (IBM Research - Tokyo)

Label Distribution Learning Machine
Jing Wang (Southeast University) · Xin Geng (Southeast University)

GraphNorm: A Principled Approach to Accelerating Graph Neural Network Training
Tianle Cai (Princeton University) · Shengjie Luo (Peking University) · Keyulu Xu (MIT) · Di He (Microsoft Research) · Tie-Yan Liu (Microsoft Research Asia) · Liwei Wang (Peking University)

Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision
Chao Jia (Google) · Yinfei Yang (Google Research) · Ye Xia (Google) · Yi-Ting Chen (Google) · Zarana Parekh (Google) · Hieu Pham (Google) · Zhen Li (Google) · Tom Duerig (Google) · Yun-Hsuan Sung (Google Research) · Quoc Le (Google Brain)

Generative Adversarial Networks for Markovian Temporal Dynamics: Stochastic Continuous Data Generation
Sung Woo Park (Chung-Ang Univ., Korea) · Dong Wook Shu (Chung-Ang Univ., Korea) · Junseok Kwon (Chun-Ang University)

Estimating $\alpha$-Rank from A Few Entries with Low Rank Matrix Completion
Yali Du (University College London) · Xue Yan (Institute of Automation, Chinese Academy of Sciences) · Xu Chen (Renmin University of China) · Jun Wang (UCL) · Haifeng Zhang (Institute of Automation, Chinese Academy of Sciences)

Geometric convergence of elliptical slice sampling
Viacheslav Natarovskii (Georg-August-Universität Göttingen) · Daniel Rudolf (Georg-August-Universität Göttingen) · Björn Sprungk (Technische Universität Bergakademie Freiberg)

A Bit More Bayesian: Domain-Invariant Learning with Uncertainty
Zehao Xiao (University of Amsterdam) · Jiayi Shen (University van Amsterdam) · Xiantong Zhen (University of Amsterdam) · Ling Shao (Inception Institute of Artificial Intelligence) · Cees Snoek (University of Amsterdam)

Convex Regularization in Monte-Carlo Tree Search
Tuan Q Dam (TU Darmstadt) · Carlo D'Eramo (TU Darmstadt) · Jan Peters (TU Darmstadt) · Joni Pajarinen (Aalto University)

Optimal Non-Convex Exact Recovery in Stochastic Block Model via Projected Power Method
Peng Wang (The Chinese University of Hong Kong) · Huikang Liu (Imperial College London) · Zirui Zhou (Huawei Technologies Canada) · Anthony Man-Cho So (The Chinese University of Hong Kong)

Sparsifying Networks via Subdifferential Inclusion
Sagar Verma (CentraleSupelec) · Jean-Christophe Pesquet (CentraleSupelec)

Efficient Message Passing for 0–1 ILPs with Binary Decision Diagrams
Jan-Hendrik Lange (University of Tübingen) · Paul Swoboda (MPI fuer Informatik, Saarbruecken)

Bayesian Algorithm Execution: Estimating Computable Properties of Black-box Functions Using Mutual Information
Willie Neiswanger (Stanford University) · Ke Alexander Wang (Stanford University) · Stefano Ermon (Stanford University)

Cyclically Equivariant Neural Decoders for Cyclic Codes
Xiangyu Chen (Tsinghua University) · Min Ye (Tsinghua Shenzhen International Graduate School)

Unitary Branching Programs: Learnability and Lower Bounds
Mateus de Oliveira Oliveira (University of Bergen) · Maria Kokkou (Chalmers University of Technology) · Fidel Ernesto Diaz Andino (University of São Paulo) · Farhad Vadiee (University of Bergen)

Dynamic Planning and Learning under Recovering Rewards
David Simchi-Levi (MIT) · Zeyu Zheng (University of California, Berkeley) · Feng Zhu (Massachusetts Institute of Technology)

Maximum Mean Discrepancy is Aware of Adversarial Attacks
Ruize Gao (Hong Kong Baptist University) · Feng Liu (University of Technology Sydney) · Jingfeng Zhang (RIKEN) · Bo Han (HKBU / RIKEN) · Tongliang Liu (The University of Sydney) · Gang Niu (RIKEN) · Masashi Sugiyama (RIKEN / The University of Tokyo)

Probabilistic Sequential Shrinking: A Best Arm Identification Algorithm for Stochastic Bandits with Corruptions
Zixin Zhong (National University of Singapore) · Wang Chi Cheung (National University of Singapore) · Vincent Tan (National University of Singapore)

Towards Rigorous Interpretations: a Formalisation of Feature Attribution
Darius Afchar (Deezer Research) · Vincent Guigue (LIP6) · Romain Hennequin (Deezer Research)

Feature Learning in Infinite-Width Neural Networks
Greg Yang (Microsoft Research) · Edward Hu (Microsoft Dynamics AI)

Self-supervised Graph-level Representation Learning with Local and Global Structure
Minghao Xu (Shanghai Jiao Tong University) · Hang Wang (Shanghai Jiao Tong University) · Bingbing Ni (Shanghai Jiao Tong University) · Hongyu Guo (National Research Council Canada) · Jian Tang (HEC Montreal & MILA)

Towards Domain-Agnostic Contrastive Learning
Vikas Verma (Aalto University) · Thang Luong (Google Brain) · Kenji Kawaguchi (Harvard University) · Hieu Pham (Google) · Quoc Le (Google Brain)

Marginal Contribution Feature Importance - an Axiomatic Approach for Explaining Data
Amnon Catav (Tel-Aviv University) · Boyang Fu (UCLA) · Yazeed Zoabi (Tel Aviv University) · Ahuva Weiss Meilik (Ichilov Medical Center) · Noam Shomron (Tel Aviv University) · Jason Ernst (UCLA) · Sriram Sankararaman (UCLA) · Ran Gilad-Bachrach (Tel-Aviv University)

Stochastic Multi-Armed Bandits with Unrestricted Delay Distributions
Tal Lancewicki (Tel-Aviv University) · Shahar Segal (Tel Aviv University) · Tomer Koren (Tel Aviv University and Google) · Yishay Mansour (Google and Tel Aviv University)

Interpretable Stein Goodness-of-fit Tests on Riemannian Manifold
Wenkai Xu (Gatsby Unit,UCL) · Takeru Matsuda (RIKEN Center for Brain Science)

Keyframe-Focused Visual Imitation Learning
Chuan Wen (Tsinghua University) · Jierui Lin (UT Austin) · Jianing Qian (University of Pennsylvania) · Yang Gao (Tsinghua University) · Dinesh Jayaraman (University of Pennsylvania)

A Nullspace Property for Subspace-Preserving Recovery
Mustafa Kaba (eBay Inc) · Chong You (University of California Berkeley) · Daniel Robinson (Lehigh University) · Enrique Mallada (Johns Hopkins University) · Rene Vidal (Johns Hopkins University, USA)

Finite mixture models do not reliably learn the number of components
Diana Cai (Princeton University) · Trevor Campbell (UBC) · Tamara Broderick (MIT)

Pareto GAN: Extending the Representational Power of GANs to Heavy-Tailed Distributions
Todd Huster (Perspecta Labs) · Jeremy Cohen (Perspecta Labs) · Zinan Lin (Carnegie Mellon University) · Kevin Chan (US army) · Charles Kamhoua (Army Research Lab) · Nandi O. Leslie (Army Research Laboratory) · Cho-Yu Chiang (Perspecta Labs) · Vyas Sekar (Carnegie Mellon University)

Generalized Doubly Reparameterized Gradient Estimators
Matthias Bauer (DeepMind) · Andriy Mnih (DeepMind)

Matrix Sketching for Secure Collaborative Machine Learning
Mengjiao Zhang (Stevens Institute of Technology) · Shusen Wang (Stevens Institute of Technology)

Improving Predictors via Combination Across Diverse Task Categories
Kwang In Kim (UNIST)

PACOH: Bayes-Optimal Meta-Learning with PAC-Guarantees
Jonas Rothfuss (ETH Zurich) · Vincent Fortuin (ETH Zürich) · Martin Josifoski (EPFL) · Andreas Krause (ETH Zurich)

Reinforcement Learning with Prototypical Representations
Denis Yarats (New York University) · Rob Fergus (Facebook / NYU) · Alessandro Lazaric (Facebook AI Research) · Lerrel Pinto (NYU/Berkeley)

MC-LSTM: Mass-Conserving LSTM
Pieter-Jan Hoedt (Ellis Unit / University Linz) · Frederik Kratzert (LIT AI Lab, Institute for Machine Learning, Johannes Kepler University Linz, Austria) · Daniel Klotz (LIT AI Lab, Institute for Machine Learning, Johannes Kepler University Linz, Austria) · Christina Halmich (LIT AI Lab, Institute for Machine Learning, Johannes Kepler University Linz, Austria) · Markus Holzleitner (LIT AI Lab / University Linz) · Grey Nearing (Google Research) · Sepp Hochreiter (LIT AI Lab, Institute for Machine Learning, Johannes Kepler University Linz, Austria) · Günter Klambauer (Johannes Kepler University Linz Austria)

Evaluating the Implicit Midpoint Integrator for Riemannian Hamiltonian Monte Carlo
James Brofos (Yale University) · Roy Lederman (Yale University)

On Monotonic Linear Interpolation of Neural Network Parameters
James Lucas (University of Toronto and Vector Institute) · Juhan Bae (University of Toronto) · Michael Zhang (University of Toronto) · Stanislav Fort (Google AI) · Richard Zemel (Vector Institute) · Roger Grosse (University of Toronto and Vector Institute)

Optimal regret algorithm for Pseudo-1d Bandit Convex Optimization
Aadirupa Saha (Indian Institute of Science (IISc), Bangalore) · Nagarajan Natarajan (Microsoft Research) · Praneeth Netrapalli (Microsoft Research) · Prateek Jain (Google Research)

Adversarial Dueling Bandits
Aadirupa Saha (Indian Institute of Science (IISc), Bangalore) · Tomer Koren (Tel Aviv University and Google) · Yishay Mansour (Google and Tel Aviv University)

Disentangling sampling and labeling bias for learning in large-output spaces
Ankit Singh Rawat (Google) · Aditya Menon (Google Research) · Wittawat Jitkrittum (Max Planck Institute for Intelligent Systems) · Sadeep Jayasumana (Google Research) · Felix Xinnan Yu (Google) · Sashank Jakkam Reddi (Google) · Sanjiv Kumar (Google Research, NY)

Rissanen Data Analysis: Examining Dataset Characteristics via Description Length
Ethan Perez (New York University) · Douwe Kiela (Facebook AI Research) · Kyunghyun Cho (New York University)

Let's Agree to Degree: Comparing Graph Convolutional Networks in the Message-Passing Framework
Floris Geerts (University of Antwerp) · Filip Mazowiecki (MPI-SWS) · Guillermo Perez (UAntwerpen)

Dueling Convex Optimization
Aadirupa Saha (Indian Institute of Science (IISc), Bangalore) · Tomer Koren (Tel Aviv University and Google) · Yishay Mansour (Google and Tel Aviv University)

GraphDF: A Discrete Flow Model for Molecular Graph Generation
Youzhi Luo (Texas A&M University) · Keqiang Yan (Texas A&M University, College Station) · Shuiwang Ji (Texas A&M University)

Implicit Bias of Linear RNNs
Melikasadat Emami (University of California Los Angeles) · Mojtaba Sahraee-Ardakan (UCLA) · Parthe Pandit (UCLA) · Sundeep Rangan (NYU) · Alyson Fletcher (UCLA)

GLSearch: Maximum Common Subgraph Detection via Learning to Search
Yunsheng Bai (UCLA) · Derek Xu (University of California, Los Angeles) · Yizhou Sun (UCLA) · Wei Wang (UCLA)

Compositional Video Synthesis with Action Graphs
Amir Bar (Tel Aviv University) · Roi Herzig (Tel Aviv University) · Xiaolong Wang (UCSD) · Anna Rohrbach (UC Berkeley) · Gal Chechik (NVIDIA / Bar-Ilan University) · Trevor Darrell (University of California at Berkeley) · Amir Globerson (Tel Aviv University, Google)

Kernel Continual Learning
Mahammad Mahdi Derakhshani (University of Amsterdam) · Xiantong Zhen (University of Amsterdam) · Ling Shao (Inception Institute of Artificial Intelligence) · Cees Snoek (University of Amsterdam)

Personalized Federated Learning using Hypernetworks
Aviv Shamsian (Bar Ilan University) · Aviv Navon (Bar-Ilan University) · Ethan Fetaya (Bar-Ilan University) · Gal Chechik (NVIDIA / Bar-Ilan University)

Memory-Efficient Graph Neural Networks
Guohao Li (KAUST) · Matthias Müller (Intel Labs) · Bernard Ghanem (KAUST) · Vladlen Koltun (Intel Labs)

Memory-Efficient Pipeline-Parallel DNN Training
Deepak Narayanan (Stanford) · Amar Phanishayee (Microsoft Research) · Kaiyu Shi (AISpeech) · Xie Chen (Microsoft) · Matei Zaharia (Stanford and Databricks)

Probabilistic Generating Circuits
Honghua Zhang (University of California, Los Angeles) · Brendan Juba (Washington University in St Louis) · Guy Van den Broeck (University of California, Los Angeles)

Connecting Optimal Ex-Ante Collusion in Teams to Extensive-Form Correlation: Faster Algorithms and Positive Complexity Results
Gabriele Farina (Carnegie Mellon University) · Andrea Celli (Facebook CDS) · Nicola Gatti (Politecnico di Milano) · Tuomas Sandholm (Carnegie Mellon University)

Near-Optimal Confidence Sequences for Bounded Random Variables
Arun Kuchibhotla (Carnegie Mellon University) · Qinqing Zheng (Facebook AI Research)

Online Unrelated Machine Load Balancing with Predictions Revisited
Shi Li (University at Buffalo) · Jiayi Xian (University at Buffalo)

Deep Reinforcement Learning amidst Continual Structured Non-Stationarity
Annie Xie (Stanford University) · James Harrison (Stanford University) · Chelsea Finn (Stanford)

Conformal prediction interval for dynamic time-series
Chen Xu (Georgia Institute of Technology) · Yao Xie (Georgia Institute of Technology)

Off-Policy Confidence Sequences
Nikos Karampatziakis (Microsoft) · Paul Mineiro (Microsoft) · Aaditya Ramdas (Carnegie Mellon University)

Break-It-Fix-It: Unsupervised Learning of Program Repair
Michihiro Yasunaga (Stanford University) · Percy Liang (Stanford University)

Deciding What to Learn: A Rate-Distortion Approach
Dilip Arumugam (Stanford University) · Benjamin Van Roy (Stanford University)

Offline Contextual Bandits with Overparameterized Models
David Brandfonbrener (NYU) · William Whitney (New York University) · Rajesh Ranganath (New York University) · Joan Bruna (New York University)

An Information-Geometric Distance on the Space of Tasks
Yansong Gao (University of Pennsylvania) · Pratik Chaudhari (University of Pennsylvania)

Deeply-Debiased Off-Policy Interval Estimation
Chengchun Shi (London School of Economics and Political Science) · Runzhe Wan (North Carolina State University) · Victor Chernozhukov (MIT) · Rui Song (North Carolina State University)

Streaming Bayesian Deep Tensor Factorization
Shikai Fang (University of Utah) · Zheng Wang (University of Utah) · Zhimeng Pan (University of Utah) · Ji Liu (Kwai Seattle AI lab, University of Rochester) · Shandian Zhe (University of Utah)

Federated Composite Optimization
Honglin Yuan (Stanford University) · Manzil Zaheer (Google Research) · Sashank Jakkam Reddi (Google)

Combinatorial Blocking Bandits with Stochastic Delays
Alexia Atsidakou (University of Texas at Austin) · Orestis Papadigenopoulos (The University of Texas at Austin) · Soumya Basu (Google) · Constantine Caramanis (University of Texas) · Sanjay Shakkottai (University of Texas at Austin)

A Proxy Variable View of Shared Confounding
Yixin Wang (Columbia University) · David Blei (Columbia University)

Provably End-to-end Label-noise Learning without Anchor Points
Xuefeng Li (University of New South Wales) · Tongliang Liu (The University of Sydney) · Bo Han (HKBU / RIKEN) · Gang Niu (RIKEN) · Masashi Sugiyama (RIKEN / The University of Tokyo)

Data Augmentation for Meta-Learning
Renkun Ni (University of Maryland) · Micah Goldblum (University of Maryland) · Amr Sharaf (University of Maryland) · Kezhi Kong (University of Maryland, College Park) · Tom Goldstein (University of Maryland)

Detection of Signal in the Spiked Rectangular Models
Ji Hyung Jung (KAIST) · Hye Won Chung (KAIST) · Ji Oon Lee (KAIST)

Interactive Learning from Activity Description
Khanh Nguyen (University of Maryland) · Dipendra Misra (Microsoft) · Robert Schapire (Microsoft Research) · Miroslav Dudik (Microsoft Research) · Patrick Shafto (Rutgers University-Newark)

Classification with Rejection Based on Cost-sensitive Classification
Nontawat Charoenphakdee (The University of Tokyo / RIKEN) · Zhenghang Cui (The University of Tokyo / RIKEN) · Yivan Zhang (The University of Tokyo / RIKEN) · Masashi Sugiyama (RIKEN / The University of Tokyo)

Putting the ``Learning" into Learning-Augmented Algorithms for Frequency Estimation
Franklyn Wang (Harvard) · Elbert Du (Harvard) · Michael Mitzenmacher (Harvard)

A Unified Lottery Ticket Hypothesis for Graph Neural Networks
Tianlong Chen (University of Texas at Austin) · Yongduo Sui (University of Science and Technology of China) · Xuxi Chen (University of Texas at Austin) · Aston Zhang (AWS AI) · Zhangyang Wang (University of Texas at Austin)

Efficient Lottery Ticket Finding: Less Data is More
Zhenyu Zhang (University of Science and Technology of China) · Xuxi Chen (University of Texas at Austin) · Tianlong Chen (University of Texas at Austin) · Zhangyang Wang (University of Texas at Austin)

UniSpeech: Unified Speech Representation Learning with Labeled and Unlabeled Data
Chengyi Wang (Nankai University) · Yu Wu (Microsoft Research) · Yao Qian (Microsoft) · Kenichi Kumatani (Microsoft) · Shujie Liu (Microsoft Research Asia) · Furu Wei (Microsoft Research Asia) · Michael Zeng (Microsoft) · Xuedong Huang (Microsoft)

Learning Diverse-Structured Networks for Adversarial Robustness
Xuefeng Du (University of Wisconsin-Madison) · Jingfeng Zhang (RIKEN) · Bo Han (HKBU / RIKEN) · Tongliang Liu (The University of Sydney) · Yu Rong (Tencent AI Lab) · Gang Niu (RIKEN) · Junzhou Huang (University of Texas at Arlington / Tencent AI Lab) · Masashi Sugiyama (RIKEN / The University of Tokyo)

Improved OOD Generalization via Adversarial Training and Pretraing
Mingyang Yi (Chinese Academy of Science) · Lu Hou (Huawei Noah's Ark Lab) · Jiacheng Sun (Huawei Noah's Ark Lab) · Lifeng Shang (Noah's Ark Lab) · Xin Jiang (Huawei Noah's Ark lab) · Qun Liu (Huawei Noah's Ark Lab) · Zhiming Ma ()

Approximation Theory of Convolutional Architectures for Time Series Modelling
Haotian Jiang (National University of Singapore) · Zhong Li (Peking University) · Qianxiao Li (National University of Singapore; IHPC, Singapore)

Conditional Temporal Neural Processes with Covariance Loss
Boseon Yoo (KAIST) · Jiwoo Lee (UNIST) · Janghoon Ju (UNIST) · Seijun Chung (Korea Advanced Institute of Science and Technology) · Soyeon Kim (Korea Advanced Institute of Science and Technology) · Jaesik Choi (KAIST)

Improving Lossless Compression Rates via Monte Carlo Bits-Back Coding
Yangjun Ruan (University of Toronto) · Karen Ullrich (FAIR) · Daniel Severo (University of Toronto) · James Townsend () · Ashish Khisti (Univ. of Toronto) · Arnaud Doucet (Oxford University) · Alireza Makhzani (University of Toronto) · Chris Maddison (University of Toronto)

Temporal Difference Learning as Gradient Splitting
Rui Liu (Boston University) · Alex Olshevsky (Boston University)

Logarithmic Regret for Reinforcement Learning with Linear Function Approximation
Jiafan He (University of California, Los Angeles) · Dongruo Zhou (UCLA) · Quanquan Gu (University of California, Los Angeles)

Machine Unlearning for Random Forests
Jonathan Brophy (University of Oregon) · Daniel Lowd (University of Oregon)

Scalable Learning of Independent Cascade Dynamics from Partial Observations
Mateusz Wilinski (Los Alamos National Laboratory) · Andrey Lokhov (Los Alamos National Laboratory)

Randomized Entity-wise Factorization for Multi-Agent Reinforcement Learning
Shariq Iqbal (University of Southern California) · Christian Schroeder (University of Oxford) · Bei Peng (University of Oxford) · Wendelin Boehmer (Delft University of Technology) · Shimon Whiteson (University of Oxford) · Fei Sha (Google Research)

Neural Tangent Generalization Attacks
Chia-Hung Yuan (National Tsing Hua University) · Shan-Hung (Brandon) Wu (National Tsing Hua University)

Top-k eXtreme Contextual Bandits with Arm Hierarchy
Rajat Sen (Amazon) · Alexander Rakhlin (MIT) · Lexing Ying (Stanford University) · Rahul Kidambi (Amazon Search & AI) · Dean Foster (Amazon) · Daniel Hill (Amazon.com, Inc.) · Inderjit Dhillon (UT Austin & Amazon)

The Implicit Bias for Adaptive Optimization Algorithms on Homogeneous Neural Networks
Bohan Wang (Microsoft Research Asia) · Qi Meng (Microsoft) · Wei Chen (Microsoft Research) · Tie-Yan Liu (Microsoft Research Asia)

Decomposition, Visualization and Analysis of Complex Features in DNNs
Jie Ren (Shanghai Jiao Tong University) · Mingjie Li (Shanghai Jiao Tong University) · Zexu Liu (Shanghai Jiao Tong University) · Quanshi Zhang (Shanghai Jiao Tong University)

SinIR: Efficient General Image Manipulation with Single Image Reconstruction
Jihyeong Yoo (HKUST) · Qifeng Chen (HKUST)

Fused Acoustic and Text Encoding for Multimodal Bilingual Pretraining and Speech Translation
Renjie Zheng (Baidu Research) · Junkun Chen (Oregon State University) · Mingbo Ma (Baidu Research) · Liang Huang (Baidu Research USA and Oregon State University)

Accelerated Algorithms for Smooth Convex-Concave Minimax Problems with O(1/k^2) Rate on Squared Gradient Norm
TaeHo Yoon (Seoul National University) · Ernest Ryu (Seoul National University)

The importance of understanding instance-level noisy labels
Yang Liu (UC Santa Cruz)

LogME: Practical Assessment of Pre-trained Models for Transfer Learning
Kaichao You (Tsinghua University) · Yong Liu (Tsinghua University) · Jianmin Wang (Tsinghua University) · Mingsheng Long (Tsinghua University)

WGAN with an Infinitely Wide Generator Has No Spurious Stationary Points
Albert No (Hongik University) · TaeHo Yoon (Seoul National University) · Kwon Sehyun (Seoul National University) · Ernest Ryu (Seoul National University)

Objective Bound Conditional Gaussian Process for Bayesian Optimization
Taewon Jeong (KAIST) · Heeyoung Kim (KAIST)

Learning Intra-Batch Connections for Deep Metric Learning
Jenny Seidenschwarz (Technical University of Munich) · Ismail Elezi (Technical University of Munich (TUM)) · Laura Leal-Taixé (TUM)

Unsupervised Representation Learning via Neural Activation Coding
Yookoon Park (Columbia University) · Sangho Lee (Seoul National University) · Gunhee Kim (Seoul National University) · David Blei (Columbia University)

Whitening for Self-Supervised Representation Learning
Aleksandr Ermolov (University of Trento) · Aliaksandr Siarohin (University of Trento) · Enver Sangineto (University of Trento) · Nicu Sebe (University of Trento)

A Scalable Deterministic Global Optimization Algorithm for Clustering Problems
Kaixun Hua (University of British Columbia) · Mingfei Shi (University of British Columbia) · Yankai Cao (University of British Columbia)

Confidence Scores Make Instance-dependent Label-noise Learning Possible
Antonin Berthon (BIOS Health) · Bo Han (HKBU / RIKEN) · Gang Niu (RIKEN) · Tongliang Liu (The University of Sydney) · Masashi Sugiyama (RIKEN / The University of Tokyo)

VoxelWorld: Simulating Embodied Agents at One Million Experiences per Second
Aleksei Petrenko (University of Southern California) · Erik Wijmans (Georgia Tech) · Brennan Shacklett (Stanford) · Vladlen Koltun (Intel Labs)

An Identifiable Double VAE For Disentangled Representations
Graziano Mita (EURECOM) · Maurizio Filippone (Eurecom) · Pietro Michiardi (EURECOM)

Testing Group Fairness via Optimal Transport Projections
Nian Si (Stanford University) · Karthyek Murthy ( Singapore University of Technology and Design) · Jose Blanchet (Stanford University) · Viet Anh Nguyen (Stanford University / VinAI Research)

Monotonic Robust Policy Optimization with Model Discrepancy
yuankun jiang (Shanghai Jiao Tong University) · Chenglin Li (Shanghai Jiao Tong University) · Wenrui Dai (Shanghai Jiao Tong University) · Junni Zou (Shanghai Jiao Tong University) · Hongkai Xiong (Shanghai Jiao Tong University)

Guided Exploration with Proximal Policy Optimization using a Single Demonstration
Gabriele Libardi (Pompeu Fabra University) · Gianni De Fabritiis (Universitat Pompeu Fabra) · Sebastian Dittert (Universitat Pompeu Fabra)

Zero-Shot Knowledge Distillation from a Decision-Based Black-Box Model
Zi Wang (UTK)

Distributionally Robust Optimization with Markovian Data
Mengmeng Li (EPFL) · Tobias Sutter (EPFL Lausanne) · Daniel Kuhn (EPFL)

Dynamic Game Theoretic Neural Optimizer
Guan-Horng Liu (Georgia Institute of Technology) · Tianrong Chen (Georgia Institute of Technology) · Evangelos Theodorou (Georgia Tech)

Oblivious Sketching for Logistic Regression
Alexander Munteanu (TU Dortmund) · Simon Omlor (TU Dortmund) · David Woodruff (Carnegie Mellon University)

Optimizing persistent homology based functions
Mathieu Carrière (Inria) · Frederic Chazal (INRIA) · Marc Glisse (INRIA) · Yuichi Ike (Fujitsu Ltd.) · Hariprasad Kannan (Independent researcher) · Yuhei Umeda (Fujitsu)

Budgeted Heterogeneous Treatment Effect Estimation
Tian Qin (Nanjing University) · Tian-Zuo Wang (Nanjing University) · Zhi-Hua Zhou (Nanjing University)

Diversity Actor-Critic: Sample-Aware Entropy Regularization for Sample-Efficient Exploration
Seungyul Han (KAIST) · Youngchul Sung (KAIST)

"Hey, that's not an ODE": Faster ODE Adjoints via Seminorms
Patrick Kidger (University of Oxford) · Tian Qi Chen (U of Toronto) · Terry Lyons (University of Oxford)

One Pass Late Fusion Multi-view Clustering
Xinwang Liu (National University of Defense Technology) · Li Liu (National University of Defense Technology) · Siwei Wang (National University of Defense Technology ) · Qing Liao (Harbin Institute of Technology (Shenzhen)) · Wenxuan Tu (National University of Defense Technology) · Chang Tang (China University of Geosciences) · Jiyuan Liu (National University of Defense Technology) · Yi Zhang (National University of Defense Technology) · En Zhu (National University of Defense Technology)

Two-way kernel matrix puncturing: towards resource-efficient PCA and spectral clustering
Romain COUILLET (University Grenoble Alpes) · Florent Chatelain (Univ. Grenoble Alpes) · Nicolas Le Bihan (CNRS)

Neural SDEs as Infinite-Dimensional GANs
Patrick Kidger (University of Oxford) · James Foster (University of Oxford) · Xuechen Li (University of Toronto) · Terry Lyons (University of Oxford)

On Perceptual Lossy Compression: The Cost of Perceptual Reconstruction and An Optimal Training Framework
Zeyu Yan (Shanghai Jiao Tong University) · Fei Wen (Shanghai Jiao Tong University) · rendong Ying (sjtu) · Chao Ma (Shanghai Jiao Tong University) · Peilin Liu (Shanghai Jiao Tong University)

On-Policy Reinforcement Learning for the Average-Reward Criterion
Yiming Zhang (New York University) · Keith Ross (New York University Shanghai)

Learning Noise Transition Matrix from Only Noisy Labels via Total Variation Regularization
Yivan Zhang (The University of Tokyo / RIKEN) · Gang Niu (RIKEN) · Masashi Sugiyama (RIKEN / The University of Tokyo)

Imitation by Predicting Observations
Andrew Jaegle (DeepMind) · Yury Sulsky (DeepMind) · Arun Ahuja (DeepMind) · Jake Bruce (DeepMind) · Rob Fergus (DeepMind) · Greg Wayne (DeepMind)

Scaling Properties of Deep Residual Networks
Alain-Sam Cohen (InstaDeep Ltd) · Rama Cont (University of Oxford) · Alain Rossier (University of Oxford) · Renyuan Xu (University of Oxford)

Improved Regret Bounds of Bilinear Bandits using Action Space Dimension Analysis
Kyoungseok Jang (KAIST) · Kwang-Sung Jun (University of Arizona) · Se-Young Yun (KAIST) · Wanmo Kang (KAIST)

Perceiver: General Perception with Iterative Attention
Andrew Jaegle (DeepMind) · Felix Axel Gimeno Gil (DeepMind) · Andy Brock (DeepMind) · Oriol Vinyals (Google DeepMind) · Andrew Zisserman (Oxford University & Google DeepMind) · Joao Carreira (DeepMind)

Moreau-Yosida $f$-divergences
Dávid Terjék (Alfréd Rényi Institute of Mathematics)

Whittle Networks: A Deep Likelihood Model for Time Series
Zhongjie Yu (TU Darmstadt) · Fabrizio Ventola (TU Darmstadt) · Kristian Kersting (TU Darmstadt)

UneVEn: Universal Value Exploration for Multi-Agent Reinforcement Learning
Tarun Gupta (University of Oxford) · Anuj Mahajan (Dept. of Computer Science, University of Oxford) · Bei Peng (University of Oxford) · Wendelin Boehmer (Delft University of Technology) · Shimon Whiteson (University of Oxford)

Barlow Twins: Self-Supervised Learning via Redundancy Reduction
Jure Zbontar (Facebook) · Li Jing (Facebook) · Ishan Misra (Facebook AI Research) · yann lecun (Facebook) · Stephane Deny (Facebook AI Research (FAIR))

Wasserstein Distributional Normalization For Robust Distributional Certification of Noisy Labeled Data
Sung Woo Park (Chung-Ang Univ., Korea) · Junseok Kwon (Chun-Ang University)

T-SCI: A Two-Stage Conformal Inference Algorithm with Guaranteed Coverage for Cox-MLP
Jiaye Teng (Tsinghua University) · Zeren Tan (Tsinghua University) · Yang Yuan (Tsinghua University)

Functional Space Analysis of Local GAN Convergence
Valentin Khrulkov (Skolkovo Institute Of Science And Technology) · Artem Babenko (Yandex) · Ivan Oseledets (Skoltech)

Augmented World Models Facilitate Zero-Shot Dynamics Generalization From a Single Offline Environment
Philip Ball (University of Oxford) · Cong Lu (University of Oxford) · Jack Parker-Holder (University of Oxford) · Stephen Roberts (University of Oxford)

Exploiting Shared Representations for Personalized Federated Learning
Liam Collins (University of Texas at Austin) · Hamed Hassani (University of Pennsylvania) · Aryan Mokhtari (UT Austin) · Sanjay Shakkottai (University of Texas at Austin)

On Energy-Based Models with Overparametrized Shallow Neural Networks
Carles Domingo-Enrich (NYU) · Alberto Bietti (NYU) · Eric Vanden-Eijnden (New York University) · Joan Bruna (New York University)

Demonstration-Conditioned Reinforcement Learning for Few-Shot Imitation
Christopher Dance (NAVER LABS Europe) · Perez Julien (Naver Labs Europe) · Théo Cachet (Naver Labs Europe)

Cross-model Back-translated Distillation for Unsupervised Machine Translation
Xuan-Phi Nguyen (Nanyang Technological University) · Shafiq Joty (Nanyang Technological University) · Thanh-Tung Nguyen (Nanyang Technological University) · Kui Wu (Institute for Infocomm Research, Singapore) · Ai Ti Aw (Institute for Infocomm Research)

Revenue-Incentive Tradeoffs in Reserve Pricing
Yuan Deng (Google Research) · Sébastien Lahaie (Google Research) · Vahab Mirrokni (Google Research) · Song Zuo (Google)

Feature Clustering for Support Identification in Extreme Regions
Hamid Jalalzai (Inria) · Rémi Leluc (Télécom Paris)

Stability and Generalization of Stochastic Gradient Methods for Minimax Problems
Yunwen Lei (University of Birmingham) · Zhenhuan Yang (SUNY Albany) · Tianbao Yang (The University of Iowa) · Yiming Ying (SUNY Albany)

Nonparametric Decomposition of Sparse Tensors
Conor Tillinghast (University of Utah) · Shandian Zhe (University of Utah)

Active Covering
Heinrich Jiang (Google Research) · Afshin Rostamizadeh (Google)

Principled Simplicial Neural Networks for Trajectory Prediction
T. Mitchell Roddenberry (Rice University) · Nicholas Glaze (Rice University) · Santiago Segarra (Rice University)

Understanding and Mitigating Accuracy Disparity in Regression
Jianfeng Chi (University of Virginia) · Yuan Tian (University of Virginia) · Geoff Gordon (Carnegie Mellon University) · Han Zhao (University of Illinois at Urbana-Champaign)

Causal Curiosity: RL Agents Discovering Self-supervised Experiments for Causal Representation Learning
Sumedh Sontakke (University of Southern California) · Arash Mehrjou (Max Planck Institute for Intelligent Systems) · Laurent Itti (University of Southern California) · Bernhard Schölkopf (MPI for Intelligent Systems Tübingen, Germany)

Consensus Control for Decentralized Deep Learning
Lingjing Kong (EPFL) · Tao Lin (EPFL) · Anastasiia Koloskova (EPFL) · Martin Jaggi (EPFL) · Sebastian Stich (EPFL)

Mixed Nash Equilibria in the Adversarial Examples Game
Laurent Meunier (Facebook/Dauphine) · Meyer Scetbon (CREST, ENSAE) · Rafael Pinot (Dauphine University - CEA LIST) · Jamal Atif (Université Paris-Dauphine) · Yann Chevaleyre (Univ. Paris Dauphine)

Navigation Turing Test (NTT): Learning to Evaluate Human-Like Navigation
Sam Devlin (Microsoft Research) · Raluca Georgescu (Microsoft Research) · Ida Momennejad (Microsoft Research) · Jaroslaw Rzepecki (Microsoft Research) · Evelyn Zuniga (Microsoft Research) · Gavin Costello (Ninja Theory) · Guy Leroy (Microsoft Research) · Ali Shaw (Ninja Theory) · Katja Hofmann (Microsoft)

Revealing the Structure of Deep Neural Networks via Convex Duality
Tolga Ergen (Stanford University) · Mert Pilanci (Stanford)

Sparse and Imperceptible Adversarial Attack via a Homotopy Algorithm
Mingkang Zhu (University of Texas at Austin) · Tianlong Chen (University of Texas at Austin) · Zhangyang Wang (University of Texas at Austin)

Global Optimality Beyond Two Layers: Training Deep ReLU Networks via Convex Programs
Tolga Ergen (Stanford University) · Mert Pilanci (Stanford)

Neural Rough Differential Equations for Long Time Series
James Morrill (University of Oxford) · Cristopher Salvi (University of Oxford) · Patrick Kidger (University of Oxford) · James Foster (University of Oxford)

Enhancing Robustness of Neural Networks through Fourier Stabilization
Netanel Raviv (Washington University in St. Louis) · Aidan Kelley (Washington University in St. Louis) · Minzhe Guo (Washington University in St. Louis) · Yevgeniy Vorobeychik (Washington University in St. Louis)

Learning from Biased Data: A Semi-Parametric Approach
Stephan Clémençon (Télécom Paris) · Yannick Guyonvarch (Télécom Paris) · Nathan NOIRY (Telecom Paris) · Patrice Bertail (Université Paris Nanterre)

Exact Gap between Generalization Error and Uniform Convergence in Random Feature Models
Zitong Yang (University of California, Berkeley) · Yu Bai (Salesforce Research) · Song Mei (UC Berkeley)

A Distribution-dependent Analysis of Meta Learning
Mikhail Konobeev (University of Alberta) · Ilja Kuzborskij (University of Milan) · Csaba Szepesvari (DeepMind/University of Alberta)

Flow-based Attribution in Graphical Models: A Recursive Shapley Approach
Raghav Singal (Amazon) · George Michailidis (University of Florida) · Hoiyi Ng (Amazon)

Discrete-Valued Latent Preference Matrix Estimation with Graph Side Information
Changhun Jo (University of Wisconsin-Madison) · Kangwook Lee (UW Madison)

Directional Graph Networks
Dominique Beaini (InVivo AI) · Saro Passaro (University of Cambridge) · Vincent Létourneau (Université de Ottawa) · Will Hamilton (McGill University and Mila) · Gabriele Corso (University of Cambridge) · Pietro Lió (University of Cambridge)

Improved Contrastive Divergence Training of Energy-Based Models
Yilun Du (MIT) · Shuang Li (MIT) · Josh Tenenbaum (MIT) · Igor Mordatch (Google Brain)

Multifidelity Acitve Search
Quan Nguyen (Washington University in St. Louis) · Arghavan Modiri (University of Toronto) · Roman Garnett (Washington University in St. Louis)

MorphVAE: Generating Neural Morphologies from 3D-Walks using a Variational Autoencoder with Spherical Latent Space
Sophie C Laturnus (University of Tübingen) · Philipp Berens (University of Tübingen)

Oneshot Differentially Private Top-k Selection
Gang Qiao (University of Michigan, Ann Arbor) · Weijie Su (University of Pennsylvania) · Li Zhang (Google)

World Model as a Graph: Learning Latent Landmarks for Planning
Lunjun Zhang (University of Toronto) · Ge Yang (University of Chicago) · Bradly Stadie (Vector Institute)

Learning Online Algorithms with Distributional Advice
Ilias Diakonikolas (University of Wisconsin-Madison) · Vasilis Kontonis (University of Wisconsin-Madison) · Christos Tzamos (UW-Madison) · Ali Vakilian (Toyota Technological Institute at Chicago) · Nikos Zarifis (UW Madison)

Tighter Bounds on the Log Marginal Likelihood of Gaussian Process Regression Using Conjugate Gradients
Artem Artemev (Imperial College London) · David Burt (University of Cambridge) · Mark van der Wilk (Imperial College London)

Representation Matters: Assessing the Importance of Subgroup Allocations in Training Data
Esther Rolf (UC Berkeley) · Theodora Worledge (UC Berkeley) · Benjamin Recht (Berkeley) · Michael Jordan (UC Berkeley)

On Estimation in Latent Variable Models
Guanhua Fang (Baidu Research) · Ping Li (Rugters University)

Exponentially Many Local Minima in Quantum Neural Networks
Xuchen You (University of Maryland) · Xiaodi Wu (University of Maryland)

Integer Programming for Causal Structure Learning in the Presence of Latent Variables
Rui Chen (University of Wisconsin-Madison) · Sanjeeb Dash (IBM Research) · Tian Gao (IBM Research)

On Variational Inference in Biclustering Models
Guanhua Fang (Baidu Research) · Ping Li (Baidu Research)

Parameterless Transductive Feature Re-representation for Few-Shot Learning
Wentao Cui (Carleton University) · Yuhong Guo (Carleton University)

Self-Damaging Contrastive Learning
Ziyu Jiang (Texas A&M University) · Tianlong Chen (University of Texas at Austin) · Bobak Mortazavi (Texas A&M University) · Zhangyang Wang (University of Texas at Austin)

Understanding invariance via feedforward inversion of discriminatively trained classifiers
Piotr Teterwak (Boston University) · Chiyuan Zhang (Google Research) · Dilip Krishnan (Google Research) · Michael Mozer (Google Research & U. Colorado Boulder)

Taylor Expansion of Discount Factors
Yunhao Tang (Columbia University) · Mark Rowland (DeepMind) · Remi Munos (DeepMind) · Michal Valko (DeepMind / Inria / ENS Paris-Saclay)

Graph Cuts Always Find a Global Optimum for Potts Models (With a Catch)
Hunter Lang (MIT) · David Sontag (Massachusetts Institute of Technology) · Aravindan Vijayaraghavan (Northwestern University)

On Linear Identifiability of Learned Representations
Geoffrey Roeder (Princeton University) · Luke Metz (Google Brain) · Durk Kingma (Google Brain)

Data-Free Knowledge Distillation for Heterogeneous Federated Learning
Zhuangdi Zhu (Michigan State University) · Junyuan Hong (Michigan State University) · Jiayu Zhou (Michigan State University)

Best Arm Identification in Graphical Bilinear Bandits
Geovani Rizk (PSL - Université Paris Dauphine & Huawei Noah's Ark Lab) · Albert Thomas (Huawei) · Igor Colin (Huawei) · Rida Laraki (CNRS (Dauphine-PSL) and University of Liverpool) · Yann Chevaleyre (Univ. Paris Dauphine)

Nonzero-Sum Stochastic Games with Potentials
David Mguni (Noah's Ark Laboratory, Huawei) · Yutong Wu (Institute of Automation, Chinese Academy of Sciences) · Yali Du (University College London) · Yaodong Yang (Huawei) · Ziyi Wang (Peking University) · Minne Li (University College London) · Ying Wen (Shanghai Jiao Tong University) · Joel Jennings (Huawei) · Jun Wang (Huawei)

Privacy-Preserving Video Classification with Convolutional Neural Networks
Sikha Pentyala (University of Washington, Tacoma) · Rafael Dowsley (Monash University) · Martine De Cock (University of Washington)

HAWQ-V3: Dyadic Neural Network Quantization
Zhewei Yao (University of California, Berkeley) · Zhen Dong (UC Berkeley) · Zhangcheng Zheng (UC Berkeley) · Amir Gholaminejad (University of California, Berkeley) · Jiali Yu (SJTU) · Eric Tan (UC Berkeley) · Leyuan Wang (Amazon) · Qijing Huang (University of California, Berkeley) · Yida Wang (Amazon) · Michael Mahoney (UC Berkeley) · EECS Kurt Keutzer (EECS, UC Berkeley)

Multi-Task Reinforcement Learning with Context-based Representations
Shagun Sodhani (Facebook AI Research) · Amy Zhang (FAIR / UC Berkeley) · Joelle Pineau (McGill, Facebook)

Online Policy Gradient for Model Free Learning of Linear Quadratic Regulators with √T Regret
Asaf Cassel (Tel Aviv University) · Tomer Koren (Tel Aviv University and Google)

Learning and Planning in Average-Reward Markov Decision Processes
Yi Wan (University of Alberta) · Abhishek Naik (University of Alberta; Amii) · Richard Sutton (DeepMind / Univ Alberta)

Connecting Interpretability and Robustness in Decision Trees through Separation
Michal Moshkovitz (UC San Diego) · Kamalika Chaudhuri (University of California at San Diego) · Yao-Yuan Yang (UCSD)

Decision-Making Under Selective Labels: Optimal Finite-Domain Policies and Beyond
Dennis Wei (IBM Research)

1-bit Adam: Communication Efficient Large-Scale Training with Adam's Convergence Speed
Hanlin Tang (University of Rochester) · Shaoduo Gan (ETH Zurich) · Ammar Ahmad Awan (Microsoft) · Samyam Rajbhandari (Microsoft) · Conglong Li (Microsoft) · Xiangru Lian (Kwai Inc.) · Ji Liu (Kwai Seattle AI lab, University of Rochester) · Ce Zhang (ETH Zurich) · Yuxiong He (Microsoft)

I-BERT: Integer-only BERT Quantization
Sehoon Kim (University of California, Berkeley) · Amir Gholaminejad (University of California, Berkeley) · Zhewei Yao (University of California, Berkeley) · Michael Mahoney (UC Berkeley) · EECS Kurt Keutzer (EECS, UC Berkeley)

SparseBERT: Rethinking the Importance Analysis in Self-attention
Han Shi (The Hong Kong University of Science and Technology) · Jiahui Gao (The University of Hong Kong) · Xiaozhe Ren (Huawei) · Hang Xu (Huawei Noah's Ark Lab) · Xiaodan Liang (Sun Yat-sen University) · Zhenguo Li (Huawei Tech. Investment, Co., Ltd) · James Kwok (Hong Kong University of Science and Technology)

Affine Invariant Analysis of Frank-Wolfe on Strongly Convex Sets
Thomas Kerdreux (INRIA) · Lewis Liu (Mila & DIRO) · Simon Lacoste-Julien (Mila, University of Montreal & Samsung SAIL Montreal) · Damien Scieur (Samsung - SAIT AI Lab, Montreal)

A Regret Minimization Approach to Iterative Learning Control
Naman Agarwal (Google Research) · Elad Hazan (Princeton University) · Anirudha Majumdar (Princeton University) · Karan Singh (Microsoft Research)

Achieving Near Instance-Optimality and Minimax-Optimality in Stochastic and Adversarial Linear Bandits Simultaneously
Chung-Wei Lee (University of Southern California) · Haipeng Luo (University of Southern California) · Chen-Yu Wei (University of Southern California) · Mengxiao Zhang (University of Southern California) · Xiaojin Zhang (The Chinese University of Hong Kong)

Attention is not all you need: pure attention loses rank doubly exponentially with depth
Yihe Dong (Google) · Jean-Baptiste Cordonnier (EPFL) · Andreas Loukas (EPFL)

Graph Contrastive Learning Automated
Yuning You (Texas A&M University) · Tianlong Chen (University of Texas at Austin) · Yang Shen (Texas A&M University) · Zhangyang Wang (University of Texas at Austin)

MetaCURE: Meta Reinforcement Learning with Empowerment-Driven Exploration
Jin Zhang (Tsinghua University) · Jianhao Wang (Tsinghua University) · Hao Hu (Tsinghua University) · Tong Chen (Tsinghua University) · Yingfeng Chen (NetEase Fuxi AI Lab) · Changjie Fan (NetEase Fuxi AI Lab) · Chongjie Zhang (Tsinghua University)

Towards Certifying $\ell_\infty$ Robustness using Neural Networks with $\ell_\infty$-dist Neurons
Bohang Zhang (Peking University) · Tianle Cai (Princeton University) · Zhou Lu (Princeton University) · Di He (Microsoft Research) · Liwei Wang (Peking University)

Online Selection Problems against Constrained Adversary
Zhihao Jiang (Stanford University) · Pinyan Lu (Shanghai University of Finance and Economics) · Zhihao Gavin Tang (Shanghai University of Finance and Economics) · Yuhao Zhang (Shanghai Jiao Tong University)

Joint Online Learning and Decision-making via Dual Mirror Descent
Alfonso Lobos Ruiz (Microsoft) · Paul Grigas (UC Berkeley) · Zheng Wen (DeepMind)

A Lower Bound for the Sample Complexity of Inverse Reinforcement Learning
Abi Komanduru (Purdue University) · Jean Honorio (Purdue University)

Global Prosody Style Transfer Without Text Transcriptions
Kaizhi Qian (MIT-IBM Watson AI Lab) · Yang Zhang (MIT-IBM Watson AI Lab) · Shiyu Chang (MIT-IBM Watson AI Lab) · Jinjun Xiong (IBM Thomas J. Watson Research Center) · Chuang Gan (MIT-IBM Watson AI Lab) · David Cox (MIT-IBM Watson AI Lab) · Mark Hasegawa-Johnson (University of Illinois)

Online Optimization in Games via Control Theory: Connecting Regret, Passivity and Poincaré Recurrence
Yun Kuen Cheung (Royal Holloway University of London) · Georgios Piliouras (Singapore University of Technology and Design)

Pointwise Binary Classification with Pairwise Confidence Comparisons
Lei Feng (College of Computer Science, Chongqing University) · Senlin Shu (Southwest University, Chongqing, China) · Nan Lu (The University of Tokyo/RIKEN) · Bo Han (HKBU / RIKEN) · Miao Xu (University of Queensland) · Gang Niu (RIKEN) · Bo An (Nanyang Technological University) · Masashi Sugiyama (RIKEN / The University of Tokyo)

Outlier-Robust Optimal Transport
Debarghya Mukherjee (University of Michigan) · Aritra Guha (Duke University) · Justin Solomon (MIT) · Yuekai Sun (University of Michigan) · Mikhail Yurochkin (IBM Research AI)

Optimal Transport Kernels for Sequential and Parallel Neural Architecture Search
Vu Nguyen (Amazon Adelaide) · Tam Le (RIKEN AIP) · Makoto Yamada (RIKEN) · Michael A Osborne (U Oxford)

Learn-to-Share: A Hardware-friendly Transfer Learning Framework Exploiting Computation and Parameter Sharing
Cheng Fu (University of California, San Diego) · Hanxian Huang (UC San Diego) · Xinyun Chen (UC Berkeley) · Yuandong Tian (Facebook AI Research) · Jishen Zhao (University of California, San Diego)

Safe Reinforcement Learning with Linear Function Approximation
Sanae Amani (University of California, Los Angeles) · Christos Thrampoulidis (University of British Columbia) · Lin Yang (UCLA)

Federated Continual Learning with Weighted Inter-client Transfer
Jaehong Yoon (KAIST) · Wonyong Jeong (Korea Advanced Institute of Science and Technology) · GiWoong Lee (Agency for Defense Development) · Eunho Yang (KAIST,AITRICS) · Sung Ju Hwang (KAIST, AITRICS)

SketchEmbedNet: Learning Novel Concepts by Imitating Drawings
Alexander Wang (University of Toronto) · Mengye Ren (Uber ATG / University of Toronto) · Richard Zemel (Vector Institute)

Marginalized Stochastic Natural Gradients for Black-Box Variational Inference
Geng Ji (Facebook AI) · Debora Sujono (University of California, Irvine) · Erik Sudderth (University of California, Irvine)

How Important is the Train-Validation Split in Meta-Learning?
Yu Bai (Salesforce Research) · Minshuo Chen (Georgia Tech) · Pan Zhou (Salesforce) · Tuo Zhao (Georgia Tech) · Jason Lee (Princeton) · Sham Kakade (University of Washington) · Huan Wang (Salesforce Research) · Caiming Xiong (Salesforce)

State Entropy Maximization with Random Encoders for Efficient Exploration
Younggyo Seo (KAIST) · Lili Chen (UC Berkeley) · Jinwoo Shin (KAIST) · Honglak Lee (Google / U. Michigan) · Pieter Abbeel (UC Berkeley & Covariant) · Kimin Lee (UC Berkeley)

The Earth Mover's Pinball Loss: Quantiles for Histogram-Valued Regression
Florian List (University of Sydney)

Grad-Match: A Gradient Matching based Data Subset Selection for Efficient Learning
Krishnateja Killamsetty (University of Texas at Dallas) · Durga S (Indian Institute of Technology Bombay) · Baharan Mirzasoleiman (Stanford University) · Ganesh Ramakrishnan (IIT Bombay) · Abir De (IIT Bombay) · Rishabh Iyer (University of Texas at Dallas)

Infinite-Dimensional Optimization for Zero-Sum Games via Variational Transport
Lewis Liu (Mila & DIRO) · Yufeng Zhang (Northwestern University) · Zhuoran Yang (Princeton) · Reza Babanezhad (University of British Columbia) · Zhaoran Wang (Northwestern U)

Binary Classification from Multiple Unlabeled Datasets via Surrogate Set Classification
Shida Lei (The University of Tokyo) · Nan Lu (The University of Tokyo/RIKEN) · Gang Niu (RIKEN) · Issei Sato (University of Tokyo / RIKEN) · Masashi Sugiyama (RIKEN / The University of Tokyo)

Learning to Generate Noise for Multi-Attack Robustness
Divyam Madaan (KAIST) · Jinwoo Shin (KAIST) · Sung Ju Hwang (KAIST, AITRICS)

Learning from Similarity-Confidence Data
Yuzhou Cao (China Agricultural University) · Lei Feng (College of Computer Science, Chongqing University) · Yitian Xu (China Agricultural University) · Bo An (Nanyang Technological University) · Gang Niu (RIKEN) · Masashi Sugiyama (RIKEN / The University of Tokyo)

Variational Auto-Regressive Gaussian Processes for Continual Learning
Sanyam Kapoor (New York University) · Theofanis Karaletsos (Facebook) · Thang Bui (University of Sydney)

The Power of Log-Sum-Exp: Sequential Density Ratio Matrix Estimation for Speed-Accuracy Optimization
Taiki Miyagawa (NEC/RIKEN) · Akinori Ebihara (NEC Biometrics Research Laboratories)

Group Fisher Pruning for Practical Network Compression
Liyang Liu (Tsinghua University) · Shilong Zhang (University of Science and Technology of China) · Zhanghui Kuang (Sensetime Ltd.) · Aojun Zhou (Sensetime&tetras.ai) · Jing-Hao Xue (University College London) · Xinjiang Wang ( SenseTime Group Ltd.) · Yimin Chen (sensetime) · Wenming Yang (Tsinghua University) · Qingmin Liao (Tsinghua Univeristy) · Wayne Zhang (SenseTime Research)

Combining Pessimism with Optimism for Robust and Efficient Model-Based Deep Reinforcement Learning
Sebastian Curi (ETH) · Ilija Bogunovic (ETH Zurich) · Andreas Krause (ETH Zurich)

TempoRL: Learning When to Act
André Biedenkapp (University of Freiburg) · Raghu Rajan (University of Freiburg) · Frank Hutter (University of Freiburg and Bosch Center for Artificial Intelligence) · Marius Lindauer (Leibniz University Hannover)

Heterogeneous Risk Minimization
Jiashuo Liu (Tsinghua University) · Zheyuan Hu (Tsinghua University) · Peng Cui (Tsinghua University) · Bo Li (Tsinghua University) · Zheyan Shen (Tsinghua University)

A Precise Performance Analysis of Support Vector Regression
Houssem Sifaou (King Abdullah University of Science and Technology (KAUST)) · Abla Kammoun (KAUST) · Mohamed-Slim Alouini (King Abdullah University of Science and Technology )

Generalizable Episodic Memory for Deep Reinforcement Learning
Hao Hu (Tsinghua University) · Jianing Ye (Peking University) · Guangxiang Zhu (Tsinghua University) · Zhizhou Ren (University of Illinois at Urbana-Champaign) · Chongjie Zhang (Tsinghua University)

Zoo-Tuning: Adaptive Transfer from A Zoo of Models
Yang Shu (Tsinghua University) · Zhi Kou (Tsinghua University) · Zhangjie Cao (Tsinghua University) · Jianmin Wang (Tsinghua University) · Mingsheng Long (Tsinghua University)

Provably Efficient Reinforcement Learning for Discounted MDPs with Feature Mapping
Dongruo Zhou (UCLA) · Jiafan He (University of California, Los Angeles) · Quanquan Gu (University of California, Los Angeles)

Explore Visual Concept Formation for Image Classification
Shengzhou Xiong (Huazhong University of Science and Technology, Wuhan, China) · Yihua Tan (Huazhong University of Science and Technology) · Guoyou Wang (HUST)

Label Inference Attacks from Log-loss Scores
Abhinav Aggarwal (Amazon Alexa) · Shiva Kasiviswanathan (Amazon) · Zekun Xu (Amazon) · Oluwaseyi Feyisetan (Amazon Research) · Nathanael Teissier (Amazon Alexa)

Unsupervised Co-part Segmentation through Assembly
Qingzhe Gao (Shandong University) · Bin Wang (Beijing Film Academy) · Libin Liu (Peking University) · Baoquan Chen (Peking University)

Unsupervised Embedding Adaptation via Early-Stage Feature Reconstruction for Few-Shot Classification
Dong Hoon Lee (KAIST) · Sae-Young Chung (KAIST)

Decentralized Single-Timescale Actor-Critic on Zero-Sum Two-Player Stochastic Games
Hongyi Guo (Northwestern University) · Zuyue Fu (Northwestern) · Zhuoran Yang (Princeton) · Zhaoran Wang (Northwestern U)

Follow-the-Regularizer-Leader Routes to Chaos in Routing Games
Jakub Bielawski (Cracow University of Economics) · Thiparat Chotibut (Chulalongkorn university) · Fryderyk Falniowski (Cracow University of Economics) · Grzegorz Kosiorowski (Cracow University of Economics) · Michał Misiurewicz (Indiana University-Purdue University Indianapolis) · Georgios Piliouras (Singapore University of Technology and Design)

Sparsity-Agnostic Lasso Bandit
Min-hwan Oh (Seoul National University) · Garud Iyengar (Columbia) · Assaf Zeevi (Columbia University)

Estimation and Quantization of Expected Persistence Diagrams
Vincent Divol (Inria - UP Saclay) · Theo Lacombe (Inria)

Adaptive Sampling for Best Policy Identification in Markov Decision Processes
Aymen Al Marjani (ENS Lyon) · Alexandre Proutiere (KTH Royal Institute of Technology)

Positive-Negative Momentum: Manipulating Stochastic Gradient Noise to Improve Generalization
Zeke Xie (The University of Tokyo/RIKEN) · Li Yuan (National Univerisity of Singapore) · Zhanxing Zhu (Peking University) · Masashi Sugiyama (RIKEN / The University of Tokyo)

Graph Mixture Density Networks
Federico Errica (University of Pisa) · Davide Bacciu (University of Pisa) · Alessio Micheli (Universita di Pisa)

No-regret Algorithms for Capturing Events in Poisson Point Processes
Mojmir Mutny (ETH Zurich) · Andreas Krause (ETH Zurich)

Learning disentangled representations via product manifold projection
Marco Fumero (La Sapienza, University of Rome) · Luca Cosmo (Sapienza University of Rome) · Simone Melzi (Sapienza University of Rome) · Emanuele Rodola (Sapienza University of Rome)

Parametric Graph for Unimodal Ranking Bandit
Camille-Sovanneary GAUTHIER (Louis Vuitton) · Romaric Gaudel (Ensai, CREST) · Elisa Fromont (Université Rennes 1, IRISA/INRIA rba) · Boammani Aser Lompo (ENS Rennes)

Towards Understanding Learning in Neural Networks with Linear Teachers
Roei Sarussi (Tel Aviv University) · Alon Brutzkus (Tel Aviv University) · Amir Globerson (Tel Aviv University, Google)

Class2Simi: A Noise Reduction Perspective on Learning with Noisy Labels
Songhua Wu (The University of Sydney) · Xiaobo Xia (The University of Sydney) · Tongliang Liu (The University of Sydney) · Bo Han (HKBU / RIKEN) · Mingming Gong (University of Melbourne) · Nannan Wang (Xidian University) · Haifeng Liu (Brain-Inspired Technology Co., Ltd.) · Gang Niu (RIKEN)

Contrastive Learning Inverts the Data Generating Process
Roland Zimmermann (University of Tübingen, International Max Planck Research School for Intelligent Systems) · Yash Sharma (University of Tübingen) · Steffen Schneider (University of Tübingen) · Wieland Brendel (University of Tübingen) · Matthias Bethge (University of Tübingen)

Federated Deep AUC Maximization for Hetergeneous Data with a Constant Communication Complexity
Zhuoning Yuan (The University of Iowa) · Zhishuai Guo (The University of Iowa) · Yi Xu (Alibaba (U.S.) Inc.) · Yiming Ying (SUNY Albany) · Tianbao Yang (The University of Iowa)

Active Learning of Continuous-time Bayesian Networks through Interventions
Dominik Linzner (Technische Universität Darmstadt) · Heinz Koeppl (TU Darmstadt)

High-Dimensional Gaussian Process Inference with Derivatives
Filip de Roos (University of Tübingen) · Alexandra Gessner (University of Tuebingen) · Philipp Hennig (University of Tübingen)

Regret Minimization in Stochastic Non-Convex Learning via a Proximal-Gradient Approach
Nadav Hallak (The Technion) · Panayotis Mertikopoulos (CNRS and Criteo AI Lab) · Volkan Cevher (EPFL)

Analyzing the tree-layer structure of Deep Forests
Ludovic Arnould (Sorbonne Universite) · Claire Boyer (LPSM, Sorbonne Université) · Erwan Scornet (École Polytechnique)

Bayesian Quadrature on Riemannian Data Manifolds
Christian Fröhlich (University of Tübingen) · Alexandra Gessner (University of Tuebingen) · Philipp Hennig (University of Tübingen) · Bernhard Schölkopf (MPI for Intelligent Systems Tübingen, Germany) · Georgios Arvanitidis (MPI for Intelligent Systems, Tübingen)

MARINA: Faster Non-Convex Distributed Learning with Compression
Eduard Gorbunov (Moscow Institute of Physics and Technology) · Konstantin Burlachenko (King Abdullah University of Science and Technology.) · Peter Richtarik (KAUST) · Zhize Li (King Abdullah University of Science and Technology (KAUST))

Meta-StyleSpeech : Multi-Speaker Adaptive Text-to-Speech Generation
Dongchan Min (KAIST) · Dong Bok Lee (KAIST) · Eunho Yang (KAIST,AITRICS) · Sung Ju Hwang (KAIST, AITRICS)

Learning Generalized Intersection Over Union for Dense Pixelwise Prediction
Jiaqian Yu (Samsung Research Institute China – Beijing) · Jingtao Xu (Samsung Research China-Beijing (SRC-B)) · Yiwei Chen (Samsung Research Institute China – Beijing) · Weiming Li (Samsung Research China – Beijing (SRC-B)) · Qiang Wang (Samsung Research China, Beijing) · ByungIn Yoo (Samsung Advanced Institute of Technology) · Jae-Joon Han (Samsung Advanced Institute of Technology)

GeomCA: Geometric Evaluation of Data Representations
Petra Poklukar (KTH Royal Institute of Technology) · Anastasiia Varava (KTH Royal Institute of Technology) · Danica Kragic (KTH)

Hierarchical VAEs Know What They Don’t Know
Jakob Drachmann Havtorn (Technical University of Denmark) · Jes Frellsen (Technical University of Denmark) · Søren Hauberg (Technical University of Denmark) · Lars Maaløe (Corti)

Inverse Constrained Reinforcement Learning
Shehryar Malik (Information Technology University) · Usman Anwar (Information Technlogy University, Lahore.) · Alireza Aghasi (Georgia State University) · Ali Ahmed (Information Technology University)

CARTL: Cooperative Adversarially-Robust Transfer Learning
Dian Chen (Wuhan University) · Hongxin Hu (University at Buffalo) · Qian Wang (Wuhan University) · Li Yinli (Wuhan University) · Cong Wang (City University of Hong Kong) · Chao Shen (Xi'an Jiaotong University) · Qi Li (Tsinghua University)

HyperHyperNetwork for the Design of Antenna Arrays
Shahar Lutati (Tel Aviv University) · Lior Wolf (Facebook AI Research and Tel Aviv University)

Self-supervised and Supervised Joint Training for Resource-rich Machine Translation
Yong Cheng (Google) · Wei Wang (Apple AI/ML) · Lu Jiang (Google Research, CMU) · Wolfgang Macherey (Google)

Skew Orthogonal Convolutions
Sahil Singla (University of Maryland) · Soheil Feizi (University of Maryland)

Dissecting Supervised Constrastive Learning
Florian Graf (University of Salzburg) · Christoph Hofer (University of Salzburg) · Marc Niethammer (UNC) · Roland Kwitt ("University of Salzburg, Austria")

Automated Graph Representation Learning with Hyperparameter Importance Explanation
Xin Wang (Tsinghua University) · Shuyi Fan (Tsinghua University) · Kun Kuang (Zhejiang University) · wenwu zhu (Tsinghua University)

Exact Optimization of Conformal Predictors via Incremental and Decremental Learning
Giovanni Cherubin (Alan Turing Institute) · Konstantinos Chatzikokolakis (Ecole Polytechnique of Paris) · Martin Jaggi (EPFL)

Symmetric Spaces for Graph Embeddings: A Finsler-Riemannian Approach
Federico Lopez (HITS - Heidelberg Institute for Theoretical Studies) · Beatrice Pozzetti (Heidelberg University) · Steve Trettel (Stanford University) · Michael Strube (Heidelberg Institute for Theoretical Studies) · Anna Wienhard (Heidelberg University)

Self-Paced Context Evaluation for Contextual Reinforcement Learning
Theresa Eimer (Leibniz Universität Hannover) · André Biedenkapp (University of Freiburg) · Frank Hutter (University of Freiburg and Bosch Center for Artificial Intelligence) · Marius Lindauer (Leibniz University Hannover)

Leveraged Weighted Loss for Partial Label Learning
Hongwei Wen (Renmin University of China) · Jingyi Cui (Peking University) · Hanyuan Hang (University of Twente) · Jiabin Liu (AI Lab, Samsung Research China - Beijing) · Yisen Wang (Peking University) · Zhouchen Lin (Peking University)

Post-selection inference with HSIC-Lasso
Tobias Freidling (University of Cambridge) · Benjamin Poignard (Osaka University / RIKEN AIP) · Héctor Climente-González (RIKEN) · Makoto Yamada (RIKEN AIP / Kyoto University)

CountSketches, Feature Hashing and the Median of Three
Kasper Green Larsen (Aarhus University, MADALGO) · Rasmus Pagh (University of Copenhagen) · Jakub Tětek (University of Copenhagen)

Momentum Residual Neural Networks
Michael Sander (ENS and CNRS) · Pierre Ablin (CNRS and ENS) · Mathieu Blondel (Google) · Gabriel Peyré (CNRS and ENS)

Neuro-algorithmic Policies Enable Fast Combinatorial Generalization
Marin Vlastelica Pogancic (Max Planck Institute for Intelligent Systems) · Michal Rolinek (Max Planck Institute for Intelligent Systems) · Georg Martius (Max Planck Institute for Intelligent Systems)

An Algorithm for Stochastic and Adversarial Bandits with Switching Costs
Chloé Rouyer (University of Copenhagen) · Yevgeny Seldin (University of Copenhagen) · Nicolò Cesa-Bianchi (University of Milan)

Scalable Marginal-Likelihood Estimation for Model Selection in Deep Learning
Alexander Immer (ETH-Z, MPI-IS) · Matthias Bauer (DeepMind) · Vincent Fortuin (ETH Zürich) · Gunnar Ratsch (ETH Zurich) · Khan Emtiyaz (RIKEN)

Black-box density function estimation using recursive partitioning
Erik Bodin (The Alan Turing Institute) · Zhenwen Dai (Spotify) · Neill Campbell (University of Bath) · Carl Henrik Ek (University of Cambridge)

Bilevel Optimization: Convergence Analysis and Enhanced Design
Kaiyi Ji (The Ohio State University) · Junjie Yang (The Ohio State University) · Yingbin LIANG (The Ohio State University)

PopSkipJump: Decision-Based Attack for Probabilistic Classifiers
Carl-Johann Simon-Gabriel (ETH Zürich) · Noman Ahmed Sheikh (ETH Zurich) · Andreas Krause (ETH Zurich)

Generalization Error Bound for Hyperbolic Ordinal Embedding
Atsushi Suzuki (University of Greenwich) · Atsushi Nitanda (The University of Tokyo / RIKEN / JST PRESTO) · Jing Wang (University of Greenwich) · Linchuan Xu (The Hong Kong Polytechnic University) · Kenji Yamanishi (The University of Tokyo) · Marc Cavazza (University of Greenwich)

Transfer-Based Semantic Anomaly Detection
Lucas Deecke (University of Edinburgh) · Lukas Ruff (TU Berlin) · Robert Vandermeulen (TU Berlin) · Hakan Bilen (University of Edinburgh)

Can Subnetwork Structure Be the Key to Out-of-Distribution Generalization?
Dinghuai Zhang (Mila) · Kartik Ahuja (Mila) · Yilun Xu (MIT) · Yisen Wang (Peking University) · Aaron Courville (Université de Montréal)

Fast Stochastic Bregman Gradient Methods: Sharp Analysis and Variance Reduction
Radu Alexandru Dragomir (Université Toulouse Capitole & ENS Paris) · Mathieu Even (INRIA - Ecole Normale Superieure) · Hadrien Hendrikx (INRIA - Ecole Normale Supérieure - PSL)

Stochastic Sign Descent Methods: New Algorithms and Better Theory
Mher Safaryan (KAUST) · Peter Richtarik (KAUST)

Persistent Homology for Link Prediction: An Interactive View
Zuoyu Yan (Peking University) · Tengfei Ma (IBM Research) · Liangcai Gao (Peking University) · Zhi Tang (Peking University) · Chao Chen (Stony Brook University)

Regret and Cumulative Constraint Violation Analysis for Online Convex Optimization with Long Term Constraints
Xinlei Yi (KTH Royal Institute of Technology) · Xiuxian Li (Tongji University) · Tao Yang (Northeastern University) · Lihua Xie (Nanyang Technological University) · Tianyou Chai (Northeastern University) · Karl Johansson (KTH)

ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision
Wonjae Kim (NAVER AI Lab) · Bokyung Son (Kakao Enterprise) · Ildoo Kim (Kakao Brain)

Delving into Deep Imbalanced Regression
Yuzhe Yang (MIT) · Kaiwen Zha (Massachusetts Institute of Technology) · YINGCONG CHEN (MIT) · Hao Wang (Rutgers University) · Dina Katabi (MIT)

Representational aspects of depth and conditioning in normalizing flows
Frederic Koehler (MIT) · Viraj Mehta (Carnegie Mellon University) · Andrej Risteski (CMU)

Skill Discovery for Exploration and Planning using Deep Skill Graphs
Akhil Bagaria (Brown University) · Jason Senthil (Brown University) · George Konidaris (Brown)

Learning to Rehearse in Long Sequence Memorization
Zhu Zhang (DAMO Academy, Alibaba Group,) · Chang Zhou (Alibaba Group) · Jianxin Ma (Alibaba Group) · Zhijie Lin (Zhejiang University) · Jingren Zhou (Alibaba Group) · Hongxia Yang (Alibaba Group) · Zhou Zhao (Zhejiang University)

Lower Bounds on Cross-Entropy Loss in the Presence of Test-time Adversaries
Arjun Nitin Bhagoji (University of Chicago) · Daniel Cullina (Penn State University) · Vikash Sehwag (Princeton University) · Prateek Mittal (Princeton University)

Dataset Dynamics via Gradient Flows in Probability Space
David Alvarez-Melis (MSR) · Nicolo Fusi (Microsoft Research)

Tilting the playing field: Dynamical loss functions for machine learning
Miguel Ruiz Garcia (Universidad Carlos III de Madrid) · Ge Zhang (University of Pennsylvania) · Samuel Schoenholz (Google Brain) · Andrea Liu (University of Pennsylvania)

Bias-Variance Reduced Local SGD for Less Heterogeneous Federated Learning
Tomoya Murata (NTT DATA Mathematical Systems Inc.) · Taiji Suzuki (The University of Tokyo / RIKEN)

Mediated uncoupled learning: Learning functions without direct input-output correspondences
Ikko Yamane (Université Paris-Dauphine, PSL Research University/RIKEN) · Junya Honda (Kyoto University / RIKEN) · Florian YGER (Universite Paris-Dauphine) · Masashi Sugiyama (RIKEN / The University of Tokyo)

Parameter-free Locally Accelerated Conditional Gradients
Alejandro Carderera (Georgia Institute of Technology) · Jelena Diakonikolas (University of Wisconsin-Madison) · Cheuk Yin Lin ( University of Wisconsin–Madison) · Sebastian Pokutta (ZIB/TUB)

Learning Queueing Policies for Organ Transplantation Allocation using Interpretable Counterfactual Survival Analysis
Jeroen Berrevoets (University of Cambridge) · Ahmed Alaa (UCLA) · Zhaozhi Qian (University of Cambridge) · James Jordon (University of Oxford) · alexander gimson (Cambridge University Hospitals) · Mihaela van der Schaar (University of Cambridge and UCLA)

f-Domain Adversarial Learning: Theory and Algorithms
David Acuna (University of Toronto, NVIDIA, Vector Institute) · Guojun Zhang (University of Waterloo) · Marc Law (NVIDIA) · Sanja Fidler (University of Toronto, NVIDIA)

A Unified Generative Adversarial Network Training via Self-Labeling and Self-Attention
Tomoki Watanabe (Toshiba Corporation) · Paolo Favaro (University of Bern)

Automatic variational inference with cascading flows
Luca Ambrogioni (Radboud University / Donders Institute) · Gianluigi Silvestri (OnePlanet Research Center) · Marcel van Gerven (Radboud University)

On the Convergence of Hamiltonian Monte Carlo with Stochastic Gradients
Difan Zou (UCLA) · Quanquan Gu (University of California, Los Angeles)

Deep Adaptive Design: Amortizing Sequential Bayesian Experimental Design
Adam Foster (University of Oxford) · Desi Ivanova (University of Oxford) · ILYAS MALIK (Amazon) · Tom Rainforth (University of Oxford)

Kernel Stein Discrepancy Descent
Anna Korba (CREST/ENSAE) · Pierre-Cyril Aubin-Frankowski (MINES ParisTech) · Szymon Majewski (Ecole Polytechnique) · Pierre Ablin (CNRS and ENS)

DG-LMC: A Turn-key and Scalable Synchronous Distributed MCMC Algorithm via Langevin Monte Carlo within Gibbs
Vincent Plassier (Polytechnique) · Maxime Vono (Lagrange Mathematics and Computing Research Center) · Alain Durmus (ENS Paris Saclay) · Eric Moulines (Ecole Polytechnique)

Adapting to Delays and Data in Adversarial Multi-Armed Bandits
András György (DeepMind) · Pooria Joulani (DeepMind)

E(n) Equivariant Graph Neural Networks
Víctor Garcia Satorras (University of Amsterdam) · Emiel Hoogeboom (University of Amsterdam) · Max Welling (University of Amsterdam & Qualcomm)

Demystifying Inductive Biases for (Beta-)VAE Based Architectures
Dominik Zietlow (Max Planck Institute for Intelligent Systems) · Michal Rolinek (Max Planck Institute for Intelligent Systems) · Georg Martius (Max Planck Institute for Intelligent Systems)

Prioritized Level Replay
Minqi Jiang (University College London) · Edward Grefenstette (Facebook AI Research & UCL) · Tim Rocktäschel (Facebook AI Research & University College London)

Meta Learning for Support Recovery in High-dimensional Precision Matrix Estimation
Qian Zhang (Purdue University) · Yilin Zheng (-) · Jean Honorio (Purdue University)

Simultaneous Similarity-based Self-Distillation for Deep Metric Learning
Karsten Roth (Heidelberg University, University of Tuebingen) · Timo Milbich (Heidelberg University) · Bjorn Ommer (Heidelberg University) · Joseph Paul Cohen (Mila, University of Montreal) · Marzyeh Ghassemi (MIT)

Variational Data Assimilation with a Learned Inverse Observation Operator
Thomas Frerix (Technical University of Munich) · Dmitrii Kochkov (Google) · Jamie Smith (Google) · Daniel Cremers (TU Munich) · Michael Brenner (Google/Harvard) · Stephan Hoyer (Google Research)

Robust Unsupervised Learning via L-statistic Minimization
Andrea Paudice (University of Milan & Istituto Italiano di Tecnologia) · Daniela Angela Parletta (University of Genoa & Istituto Italiano di Tecnologia) · Andreas Maurer () · Massimiliano Pontil ( Istituto Italiano di Tecnologia & University College London)

Active Testing: Sample-Efficient Model Evaluation
Jannik Kossen (University of Oxford) · Sebastian Farquhar (University of Oxford) · Yarin Gal (University of Oxford) · Tom Rainforth (University of Oxford)

Reserve Price Optimization for First Price Auctions
Zhe Feng (Harvard University) · Sébastien Lahaie (Google Research) · Jon Schneider (Google) · Jinchao Ye (Google)

Grid-Functioned Neural Networks
Javier Dehesa (University of Bath) · Andrew Vidler (Ninja Theory) · Julian Padget (University of Bath) · Christof Lutteroth (University of Bath)

Dimensionality Reduction for the Sum-of-Distances Metric
Zhili Feng (Carnegie Mellon University) · Praneeth Kacham (Carnegie Mellon University) · David Woodruff (Carnegie Mellon University)

OmniNet: Omnidirectional Representations from Transformers
Yi Tay (Google) · Mostafa Dehghani (Google Brain) · Vamsi Aribandi (BITS Pilani - Hyderabad) · Jai Gupta (Google) · Philip Pham (Google Research) · Zhen Qin (Google) · Dara Bahri (Google Research) · Da-Cheng Juan (Google) · Don Metzler (Google)

Provably Correct Optimization and Exploration with Non-linear Policies
Fei Feng (UCLA) · Wotao Yin (Alibaba US) · Alekh Agarwal (Microsoft Research) · Lin Yang (UCLA)

Amortized Conditional Normalized Maximum Likelihood: Reliable Out of Distribution Uncertainty Estimation
Aurick Zhou (UC Berkeley) · Sergey Levine (UC Berkeley)

Synthesizer: Rethinking Self-Attention for Transformer Models
Yi Tay (Google) · Dara Bahri (Google Research) · Don Metzler (Google) · Da-Cheng Juan (Google) · Zhe Zhao (Google AI) · Che Zheng (Google)

Weight-covariance alignment for adversarially robust neural networks
Panagiotis Eustratiadis (University of Edinburgh) · Henry Gouk (University of Edinburgh) · Da Li (Samsung) · Timothy Hospedales (Samsung AI Centre / University of Edinburgh)

Fair Selective Classification Via Sufficiency
Joshua Lee (Massachusetts Institute of Technology) · Yuheng Bu (MIT) · Deepta Rajan (IBM Research) · Prasanna Sattigeri (IBM Research) · Rameswar Panda (MIT-IBM Watson AI Lab, IBM Research) · Subhro Das (MIT-IBM Watson AI Lab, IBM Research) · Gregory Wornell (MIT)

Mandoline: Model Evaluation under Distribution Shift
Mayee Chen (Stanford University) · Karan Goel (Stanford University) · Nimit Sohoni (Stanford University) · Fait Poms (Stanford) · Kayvon Fatahalian (Stanford) · Christopher Re (Stanford)

Optimal Thompson Sampling strategies for support-aware CVaR bandits
Dorian Baudry (CNRS/INRIA) · Romain Gautron (CIRAD - CGIAR) · Emilie Kaufmann (CNRS, Univ. Lille) · Odalric-Ambrym Maillard (Inria Lille - Nord Europe)

SECANT: Self-Expert Cloning for Zero-Shot Generalization of Visual Policies
Jim Fan (Stanford University) · Guanzhi Wang (Stanford University) · De-An Huang (NVIDIA) · Zhiding Yu (NVIDIA) · Li Fei-Fei (Stanford University) · Yuke Zhu (University of Texas - Austin) · Anima Anandkumar (Caltech and NVIDIA)

Learning Randomly Perturbed Structured Predictors for Direct Loss Minimization
Hedda Cohen Indelman (Technion) · Tamir Hazan (Technion)

On Limited-Memory Subsampling Strategies for Bandits
Dorian Baudry (CNRS/INRIA) · Yoan Russac (ENS Paris) · Olivier Cappé (ENS Paris)

High Confidence Generalization for Reinforcement Learning
James Kostas (University of Massachusetts Amherst) · Yash Chandak (University of Massachusetts Amherst) · Scott M Jordan (University of Massachusetts) · Georgios Theocharous (Adobe Research) · Philip Thomas (University of Massachusetts Amherst)

Optimizing Black-box Metrics with Iterative Example Weighting
Gaurush Hiranandani (UIUC) · Jatin Mathur (University of Illinois at Urbana-Champaign) · Sanmi Koyejo (Illinois / Google) · Mahdi Milani Fard (Google) · Harikrishna Narasimhan (Google Research)

Robust Asymmetric Learning in POMDPs
Andrew Warrington (University of Oxford) · Jonathan Lavington (University of British Columbia) · Adam Scibior (University of British Columbia) · Mark Schmidt (University of British Columbia) · Frank Wood (University of British Columbia)

Risk-Sensitive Reinforcement Learning with Function Approximation: A Debiasing Approach
Yingjie Fei (Cornell University) · Zhuoran Yang (Princeton University) · Zhaoran Wang (Northwestern U)

Online Limited Memory Neural-Linear Bandits with Likelihood Matching
Ofir Nabati (Technion) · Tom Zahavy (DeepMind) · Shie Mannor (Technion)

Provable Meta-Learning of Linear Representations
Nilesh Tripuraneni (UC Berkeley) · Chi Jin (Princeton University) · Michael Jordan (UC Berkeley)

Oops I Took A Gradient: Scalable Sampling for Discrete Distributions
Will Grathwohl (University of Toronto) · Kevin Swersky (Google Brain) · Milad Hashemi (Google) · David Duvenaud (University of Toronto) · Chris Maddison (University of Toronto)

A Collective Learning Framework to Boost GNN Expressiveness for Node Classification
Mengyue Hang (Purdue University) · Jennifer Neville (Purdue University) · Bruno Ribeiro (Purdue University)

Provably Efficient Algorithms for Multi-Objective Competitive RL
Tiancheng Yu (MIT) · Yi Tian (Massachusetts Institute of Technology) · Jingzhao Zhang (MIT) · Suvrit Sra (MIT)

Online Learning in Unknown Markov Games
Yi Tian (Massachusetts Institute of Technology) · Yuanhao Wang (Princeton University) · Tiancheng Yu (MIT) · Suvrit Sra (MIT)

Decoupling Value and Policy for Generalization in Reinforcement Learning
Roberta Raileanu (NYU) · Rob Fergus (Facebook / NYU)

Value Iteration in Continuous Actions, States and Time
Michael Lutter (Technical University of Darmstadt) · Shie Mannor (Technion) · Jan Peters (TU Darmstadt) · Dieter Fox (NVIDIA) · Animesh Garg (University of Toronto, Vector Institute, Nvidia)

Policy Caches with Successor Features
Mark Nemecek (Duke University) · Ron Parr (Duke University)

Neighborhood Contrastive Learning Applied to Online Patient Monitoring
Hugo Yèche (ETH Zürich) · Gideon Dresdner (ETH Zürich) · Francesco Locatello (ETH Zurich - Max Planck Institute) · Matthias Hüser (ETH Zürich) · Gunnar Rätsch (ETH Zurich)

On Disentangled Representations Learned from Correlated Data
Frederik Träuble (MPI for Intelligent Systems) · Elliot Creager (University of Toronto) · Niki Kilbertus (Helmholtz AI) · Francesco Locatello (Amazon) · Andrea Dittadi (Technical University of Denmark) · Anirudh Goyal (Université de Montréal) · Bernhard Schölkopf (MPI for Intelligent Systems Tübingen, Germany) · Stefan Bauer (MPI for Intelligent Systems)

Query Complexity of Adversarial Attacks
Grzegorz Gluch (EPFL) · Rüdiger Urbanke (EPFL)

How to learn when data reacts to your model: performative gradient descent
Zachary Izzo (Stanford University) · Lexing Ying (Stanford University) · James Zou (Stanford University)

Diffusion Source Identification on Networks with Statistical Confidence
Quinlan Dawkins (University of Virginia) · Tianxi Li (University of Virginia) · Haifeng Xu (University of Virginia)

Differentially Private Query Release Through Adaptive Projection
Sergul Aydore (Amazon Web Services) · William Brown (Columbia University) · Michael Kearns (University of Pennsylvania) · Krishnaram Kenthapadi (Amazon AWS AI) · Luca Melis (Amazon Web Services) · Aaron Roth (University of Pennsylvania) · Ankit Siva (Amazon)

Robust Testing and Estimation under Manipulation Attacks
Jayadev Acharya (Cornell University) · Ziteng Sun (Cornell University) · Huanyu Zhang (Facebook)

Ornstein-Uhlenbeck Smoothing for Hierarchical Variational Autoencoders
Adeel Pervez (University of Amsterdam) · Efstratios Gavves (University of Amsterdam )

Learning Routines for Effective Off-Policy Reinforcement Learning
Edoardo Cetin (King's College London) · Oya Celiktutan (King's College London)

Markpainting: Adversarial Machine Learning meets Inpainting
David G Khachaturov (University of Cambridge) · Ilia Shumailov (University of Cambridge) · Yiren Zhao (University of Cambridge) · Nicolas Papernot (University of Toronto and Vector Institute) · Ross Anderson (University of Cambridge)

Online A-Optimal Design and Active Linear Regression
Xavier Fontaine (ENS Paris-Saclay) · Pierre Perrault (ENS Paris Saclay & Inria) · Michal Valko (DeepMind / Inria / ENS Paris-Saclay) · Vianney Perchet (ENSAE & Criteo AI Lab)

Continual Learning in the Teacher-Student Setup: Impact of Task Similarity
Sebastian Lee (Microsoft Research) · Sebastian Goldt (International School of Advanced Studies (SISSA)) · Andrew Saxe (University of Oxford)

Fast Projection Onto Convex Smooth Constraints
Ilnura Usmanova (ETH Zurich) · Kfir Levy (-) · Maryam Kamgarpour (University of British Columbia) · Andreas Krause (ETH Zurich)

Selfish Sparse RNN Training
Shiwei Liu (Eindhoven University of Technology) · Decebal Constantin Mocanu (University of Twente) · Yulong Pei (TU Eindhoven) · Mykola Pechenizkiy (TU Eindhoven)

Data-driven prediction of general Hamiltonian dynamics via learning exactly-symplectic maps
Renyi Chen (Georgia Institute of Technology) · Molei Tao (Georgia Institute of Technology)

The Logical Options Framework
Brandon Araki (MIT) · Xiao Li (MIT) · Kiran Vodrahalli (Columbia University) · Jonathan DeCastro (Toyota Research Institute) · Micah Fry (MIT Lincoln Laboratory) · Daniela Rus (MIT CSAIL)

Sample Complexity of Robust Linear Classification on Separated Data
Robi Bhattacharjee (UCSD) · Somesh Jha (University of Wisconsin, Madison) · Kamalika Chaudhuri (University of California at San Diego)

Confidence-Budget Matching for Sequential Budgeted Learning
Yonathan Efroni (Microsoft Research, New York) · Nadav Merlis (Technion) · Aadirupa Saha (Indian Institute of Science (IISc), Bangalore) · Shie Mannor (Technion)

Emergent Social Learning via Multi-agent Reinforcement Learning
Kamal Ndousse (OpenAI) · Douglas Eck (Google Brain) · Sergey Levine (UC Berkeley) · Natasha Jaques (Google Brain, UC Berkeley)

Multi-Receiver Online Bayesian Persuasion
Matteo Castiglioni (Politecnico di Milano) · Alberto Marchesi (Politecnico di Milano) · Andrea Celli (Facebook CDS) · Nicola Gatti (Politecnico di Milano)

Fast Sketching of Polynomial Kernels of Polynomial Degree
Zhao Song (UT-Austin & University of Washington) · David Woodruff (Carnegie Mellon University) · Zheng Yu (Princeton University) · Lichen Zhang (Carnegie Mellon University)

DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning
Wei-Fang Sun (National Tsing Hua University) · Cheng-Kuang Lee (NVIDIA Corporation) · Chun-Yi Lee (National Tsing Hua University)

Principal Component Hierarchy for Sparse Quadratic Programs
Robbie Vreugdenhil (TU Delft) · Viet Anh Nguyen (Stanford University / VinAI Research) · Armin Eftekhari (Umea University) · Peyman Mohajerin Esfahani (Delft University of Technology)

Analysis of stochastic Lanczos quadrature for spectrum approximation
Tyler Chen (University of Washington) · Thomas Trogdon (University of Washington) · Shashanka Ubaru (IBM Research)

Shortest-Path Constrained Reinforcement Learning for Sparse Reward Tasks
Sungryull Sohn (University of Michigan) · Sungtae Lee (Yonsei University) · Jongwook Choi (University of Michigan) · Harm van Seijen (Microsoft Research) · Mehdi Fatemi (Microsoft Research) · Honglak Lee (Google / U. Michigan)

Sliced Iterative Normalizing Flows
Biwei Dai (University of California, Berkeley) · Uros Seljak (UC Berkeley)

The Power of Adaptivity for Stochastic Submodular Cover
Rohan Ghuge (University of Michigan) · Anupam Gupta (Carnegie Mellon University) · viswanath nagarajan (Univ Michigan, Ann Arbor)

Decomposable Submodular Function Minimization via Maximum Flow
Kyriakos Axiotis (MIT) · Adam Karczmarz (University of Warsaw) · Anish Mukherjee (University of Warsaw) · Piotr Sankowski (IDEAS NCBR, MIM Solutions & University of Warsaw) · Adrian Vladu (CNRS & IRIF, University of Paris)

Bilinear Classes: A Structural Framework for Provable Generalization in RL
Simon Du (University of Washington) · Sham Kakade (University of Washington) · Jason Lee (Princeton) · Shachar Lovett (University of California San Diego) · Gaurav Mahajan (UCSD) · Wen Sun (Cornell University) · Ruosong Wang (Carnegie Mellon University)

Learning to Price Against a Moving Target
Renato Leme (Google Research) · Balasubramanian Sivan (Google Research) · Yifeng Teng (University of Wisconsin-Madison) · Pratik Worah (Google)

GP-Tree: A Gaussian Process Classifier for Few-Shot Incremental Learning
Idan Achituve (Bar-Ilan) · Aviv Navon (Bar-Ilan University) · Yochai Yemini (Bar-Ilan University) · Gal Chechik (NVIDIA / Bar-Ilan University) · Ethan Fetaya (Bar-Ilan University)

Examining and Combating Spurious Features under Distribution Shift
Chunting Zhou (Carnegie Mellon University) · Xuezhe Ma (University of Southern California) · Paul Michel (Carnegie Mellon University) · Graham Neubig (Carnegie Mellon University)

Permutation Weighting
David Arbour (Adobe Research) · Drew Dimmery (University of Vienna) · Arjun Sondhi (University of Washington)

Deep kernel processes
Laurence Aitchison (University of Bristol) · Adam Yang (University of Bristol) · Sebastian Ober (University of Cambridge)

PAC-Learning for Strategic Classification
Ravi Sundaram (Northeastern) · Anil Vullikanti (Biocomplexity Institute and Dept of Computer Science, University of Virginia) · Haifeng Xu (University of Virginia) · Fan Yao (University of Virginia)

Global inducing point variational posteriors for Bayesian neural networks and deep Gaussian processes
Sebastian Ober (University of Cambridge) · Laurence Aitchison (University of Bristol)

Robust Inference for High-dimensional Linear Models via Residual Randomization
Y. Samuel Wang (University of Chicago) · Si Kai Lee (Chicago Booth School of Business) · Panos Toulis (Chicago Booth School of Business) · Mladen Kolar (University of Chicago Booth School of Business)

XOR-CD: Linearly Convergent Constrained Structure Generation
Fan Ding (Purdue University) · Jianzhu Ma (Institute for Artificial Intelligence) · Jinbo Xu (Toyota Technological Institute at Chicago) · Yexiang Xue (Purdue University)

Besov Function Approximation and Binary Classification on Low-Dimensional Manifolds Using Convolutional Residual Networks
Hao Liu (Hong Kong Baptist University) · Minshuo Chen (Georgia Tech) · Tuo Zhao (Georgia Tech) · Wenjing Liao (Georgia Tech)

Just Train Twice: Improving Group Robustness without Training Group Information
Evan Liu (Stanford University) · Behzad Haghgoo (Stanford University) · Annie Chen (Stanford University) · Aditi Raghunathan (Stanford) · Pang Wei Koh (Stanford University) · Shiori Sagawa (Stanford University) · Percy Liang (Stanford University) · Chelsea Finn (Stanford)

On Proximal Policy Optimization's Heavy-tailed Gradients
Saurabh Garg (Carnegie Mellon University) · Joshua Zhanson (Carnegie Mellon University) · Emilio Parisotto (Carnegie Mellon University) · Adarsh Prasad (Carnegie Mellon University) · Zico Kolter (Carnegie Mellon University / Bosch Center for AI) · Sivaraman Balakrishnan (CMU) · Zachary Lipton (Carnegie Mellon University) · Ruslan Salakhutdinov (Carnegie Mellen University) · Pradeep Ravikumar (Carnegie Mellon University)

The Symmetry between Arms and Knapsacks: A Primal-Dual Approach for Bandits with Knapsacks
Xiaocheng Li (Imperial College London) · Chunlin Sun (Stanford University) · Yinyu Ye (Standord)

Sparse within Sparse Gaussian Processes using Neighbor Information
Gia-Lac Tran (EURECOM) · Dimitrios Milios (EURECOM) · Pietro Michiardi (EURECOM) · Maurizio Filippone (Eurecom)

Slot Machines: Discovering Winning Combinations of Random Weights in Neural Networks
Maxwell Aladago (Dartmouth College) · Lorenzo Torresani (Dartmouth & Facebook AI)

Signatured Deep Fictitious Play for Mean Field Games with Common Noise
Ming Min (University of California, Santa Barbara) · Ruimeng Hu (University of California, Santa Barbara)

Data Diversity Matters: How and Why to Use Experimental Data to Evaluate Methods for Observational Causal Inference
Amanda Gentzel (University of Massachusetts Amherst) · Purva Pruthi (University of Massachusetts Amherst) · David Jensen (University of Massachusetts Amherst)

Local Correlation Clustering with Asymmetric Classification Errors
Jafar Jafarov (University of Chicago) · Sanchit Kalhan (Northwestern University) · Konstantin Makarychev (Northwestern University) · Yury Makarychev (Toyota Technological Institute at Chicago)

Sample Efficient Reinforcement Learning In Continuous State Spaces: A Perspective Beyond Linearity
Dhruv Malik (Carnegie Mellon University) · Aldo Pacchiano (UC Berkeley) · Vishwak Srinivasan (Carnegie Mellon University) · Yuanzhi Li (CMU)

AlphaNet: Improved Training of Supernet with Alpha-Divergence
Dilin Wang (Facebook) · Chengyue Gong (UT Austin) · Meng Li (Facebook Inc) · Qiang Liu (UT Austin) · Vikas Chandra (Facebook)

The Impact of Record Linkage on Learning from Feature Partitioned Data
Richard Nock (Google Brain) · Stephen J Hardy (Ambiata) · Wilko Henecka (Data61) · Hamish Ivey-Law (ANU) · Jakub Nabaglo (None) · Giorgio Patrini (Sensity) · Guillaume Smith (Ambiata) · Brian Thorne (HardByte)

Deep Continuous Networks
Nergis Tomen (Delft University of Technology) · Silvia-Laura Pintea (TU Delft) · Jan van Gemert (Delft University of Technology)

Provable Lipschitz Certification for Generative Models
Matt Jordan (University of Texas at Austin) · Alexandros Dimakis (UT Austin)

Acceleration via Fractal Learning Rate Schedules
Naman Agarwal (Google Research) · Surbhi Goel (Microsoft Research) · Cyril Zhang (Microsoft Research)

Structured Convolutional Kernel Networks for Airline Crew Scheduling
Yassine Yaakoubi (Mila, McGill University) · Francois Soumis ( Polytechnique, Montreal) · Simon Lacoste-Julien (Mila, University of Montreal & Samsung SAIL Montreal)

Improved Regret Bound and Experience Replay in Regularized Policy Iteration
Nevena Lazic (DeepMind) · Dong Yin (DeepMind) · Yasin Abbasi-Yadkori (Adobe Research) · Csaba Szepesvari (DeepMind/University of Alberta)

Benchmarks, Algorithms, and Metrics for Hierarchical Disentanglement
Andrew Ross (Harvard University) · Finale Doshi-Velez (Harvard University)

TeraPipe: Token-Level Pipeline Parallelism for Training Large-Scale Language Models
Zhuohan Li (UC Berkeley) · Siyuan Zhuang (UC Berkeley) · Shiyuan Guo (University of California, Berkeley) · Danyang Zhuo (Duke University) · Hao Zhang (CMU) · Dawn Song (University of California, Berkeley) · Ion Stoica (UC Berkeley)

Bayesian Optimization over Hybrid Spaces
Aryan Deshwal (Washington State University) · Syrine Belakaria (Washington state university) · Jana Doppa (Washington State University)

Out-of-Distribution Generalization via Risk Extrapolation (REx)
David Krueger (Universit? de Montr?al) · Ethan Caballero (Mila) · Joern-Henrik Jacobsen (Apple Inc.) · Amy Zhang (FAIR / UC Berkeley) · Jonathan Binas (Mila, Montreal) · Dinghuai Zhang (Mila) · Remi Le Priol (Mila, Université de Montréal) · Aaron Courville (Université de Montréal)

Multiplicative noise and heavy tails in stochastic optimization
Liam Hodgkinson (University of California Berkeley) · Michael Mahoney (UC Berkeley)

Near-optimal algorithms for explainable k-medians and k-means
Konstantin Makarychev (Northwestern University) · Liren Shan (Northwestern University)

Task-Optimal Exploration in Linear Dynamical Systems
Andrew Wagenmaker (University of Washington) · Max Simchowitz (UC Berkeley) · Kevin Jamieson (University of Washington)

DORO: Distributional and Outlier Robust Optimization
Runtian Zhai (Carnegie Mellon University) · Chen Dan (Carnegie Mellon University) · Zico Kolter (Carnegie Mellon University / Bosch Center for AI) · Pradeep Ravikumar (Carnegie Mellon University)

SimAM: A Simple, Parameter-Free Attention Module for Convolutional Neural Networks
Lingxiao YANG (Sun Yat-sen University) · Ru-Yuan Zhang (Shanghai Jiao Tong University) · Lida LI (The Hong Kong Polytechnic University) · Xiaohua Xie (Sun Yat-sen University)

Parallel tempering on optimized paths
Saifuddin Syed (University of British Columbia) · Vittorio Romaniello (University of British Columbia) · Trevor Campbell (UBC) · Alexandre Bouchard-Côté (UBC)

LEGO: Latent Execution-Guided Reasoning for Multi-Hop Question Answering on Knowledge Graphs
Hongyu Ren (Stanford University) · Hanjun Dai (Google Brain) · Bo Dai (Google Brain) · Xinyun Chen (UC Berkeley) · Michihiro Yasunaga (Stanford University) · Haitian Sun (Google) · Dale Schuurmans (Google / University of Alberta) · Jure Leskovec (Stanford University) · Denny Zhou (Google Brain)

Group-Sparse Matrix Factorization for Transfer Learning of Word Embeddings
Kan Xu (University of Pennsylvania) · Xuanyi Zhao (University of Pennsylvania) · Hamsa Bastani (Wharton) · Osbert Bastani (University of Pennsylvania)

Tightening the Dependence on Horizon in the Sample Complexity of Q-Learning
Gen Li (Tsinghua University, China) · Changxiao Cai (Princeton University) · Yuxin Chen (Princeton University) · Yuantao Gu (Tsinghua University) · Yuting Wei (Carnegie Mellon University) · Yuejie Chi (CMU)

Order-Agnostic Cross Entropy for Non-Autoregressive Machine Translation
Cunxiao Du (SMU_SG) · Zhaopeng Tu (Tencent AI Lab) · Jing Jiang (Singapore Management University)

The Emergence of Individuality in Multi-Agent Reinforcement Learning
Jiechuan Jiang (Peking University) · Zongqing Lu (Peking University)

A hybrid variance-reduced method for decentralized stochastic non-convex optimization
Ran Xin (Carnegie Mellon University) · Usman Khan (Tufts University) · Soummya Kar (Carnegie Mellon University)

Interaction-Grounded Learning
Tengyang Xie (University of Illinois at Urbana-Champaign) · John Langford (Microsoft Research) · Paul Mineiro (Microsoft) · Ida Momennejad (Microsoft Research)

Large-Scale Meta-Learning with Continual Trajectory Shifting
JaeWoong Shin (KAIST) · Hae Beom Lee (KAIST) · Boqing Gong (Google) · Sung Ju Hwang (KAIST, AITRICS)

Is Space-Time Attention All You Need for Video Understanding?
Gedas Bertasius (Facebook AI) · Heng Wang (Facebook Research) · Lorenzo Torresani (Facebook AI)

MURAL: Meta-Learning Uncertainty-Aware Rewards for Outcome-Driven Reinforcement Learning
Kevin Li (UC Berkeley) · Abhishek Gupta (UC Berkeley) · Ashwin D Reddy (UC Berkeley) · Vitchyr Pong (UC Berkeley) · Aurick Zhou (UC Berkeley) · Justin Yu (Berkeley) · Sergey Levine (UC Berkeley)

EfficientTTS: An Efficient and High-Quality Text-to-Speech Architecture
Chenfeng Miao (Ping An Technology) · Liang Shuang (PingAn Technology) · Zhengchen Liu (Ping An Technology) · Chen Minchuan (PingAn Technology) · Jun Ma (Ping An Technology) · Shaojun Wang (PAII Inc.) · Jing Xiao (Ping An Insurance (Group) Company of China)

Cooperative Exploration for Multi-Agent Deep Reinforcement Learning
Iou-Jen Liu (University of Illinois at Urbana-Champaign) · Unnat Jain (UIUC) · Raymond Yeh (University of Illinois at Urbana–Champaign) · Alexander Schwing (UIUC)

A Wasserstein Minimax Framework for Mixed Linear Regression
Theo Diamandis (MIT) · Yonina Eldar () · Alireza Fallah (MIT) · Farzan Farnia (Massachusetts Institute of Technology) · Asuman Ozdaglar (MIT)

Scalable Computations of Wasserstein Barycenter via Input Convex Neural Networks
Yongxin Chen (Georgia Institute of Technology) · Jiaojiao Fan (Georgia Institute of Technology) · Amirhossein Taghvaei (University of Callifornia, Irvine)

Sharper Generalization Bounds for Clustering
Shaojie Li (Renmin University of China) · Yong Liu (Renmin University of China)

Cross-domain Imitation from Observation
Dripta S. Raychaudhuri (University of California, Riverside) · Sujoy Paul (Google Research) · Jeroen Vanbaar (MERL) · Amit K. Roy-Chowdhury (University of California, Riverside)

Asynchronous Decentralized Optimization with Implicit Stochastic Variance Reduction
Kenta Niwa (NTT) · Guoqiang Zhang (University of Technology Sydney) · W. Bastiaan Kleijn (Victoria University of Wellington) · Noboru Harada (NTT) · Hiroshi Sawada (NTT Corporation) · Akinori Fujino (NTT)

Learning Stochastic Behaviour from Aggregate Data
Shaojun Ma (Georgia Tech) · Shu Liu (Georgia Institute of Technology) · Hongyuan Zha (Georgia Institute of Technology) · Haomin Zhou (Georgia Institute of Technology)

Global Convergence of Policy Gradient for Linear-Quadratic Mean-Field Control/Game in Continuous Time
Weichen Wang (The University of Hong Kong) · Jiequn Han (Princeton University) · Zhuoran Yang (Princeton University) · Zhaoran Wang (Northwestern)

Order Matters: Probabilistic Modeling of Node Sequence for Graph Generation
Xiaohui Chen (Tufts University) · Xu Han (Tufts University) · Jiajing Hu (Tufts University) · Francisco R Ruiz (DeepMind) · Liping Liu (Tufts University)

Straight to the Gradient: Learning to Use Novel Tokens for Neural TextGeneration
Xiang Lin (Nanyang Techonological University) · Simeng Han (Nanyang Technological University) · Shafiq Joty (Nanyang Technological University)

Towards Better Laplacian Representation in Reinforcement Learning with Generalized Graph Drawing
Kaixin Wang (National University of Singapore) · Kuangqi Zhou (National University of Singapore) · Qixin Zhang (city university of hong kong) · Jie Shao (Fudan University) · Bryan Hooi (National University of Singapore) · Jiashi Feng (National University of Singapore)

Model-Free and Model-Based Policy Evaluation when Causality is Uncertain
David Bruns-Smith (UC Berkeley)

GMAC: A Distributional Perspective on Actor-Critic Framework
Daniel Nam (KC Machine Learning Lab) · Younghoon Kim (KC-ML2) · Chan Youn Park (KC ML2)

Provable Robustness of Adversarial Training for Learning Halfspaces with Noise
Difan Zou (UCLA) · Spencer Frei (UCLA) · Quanquan Gu (University of California, Los Angeles)

Continuous Coordination As a Realistic Scenario for Lifelong Learning
Hadi Nekoei (MILA) · Akilesh Badrinaaraayanan (Mila / University of Montreal) · Aaron Courville (Université de Montréal) · Sarath Chandar (Mila / École Polytechnique de Montréal)

Offline Reinforcement Learning with Fisher Divergence Critic Regularization
Ilya Kostrikov (UC Berkeley) · Rob Fergus (DeepMind) · Jonathan Tompson (Google Brain) · Ofir Nachum (Google Brain)

Towards Practical Mean Bounds for Small Samples
My Phan (University of Massachusetts Amherst) · Philip Thomas (University of Massachusetts Amherst) · Erik Learned-Miller (University of Massachusetts, Amherst)

A Sharp Analysis of Model-based Reinforcement Learning with Self-Play
Qinghua Liu (Princeton University) · Tiancheng Yu (MIT) · Yu Bai (Salesforce Research) · Chi Jin (Princeton University)

Spectral vertex sparsifiers and pair-wise spanners over distributed graphs
Chunjiang Zhu (University of North Carolina Greensboro) · Qinqing Liu (University of Connecticut) · Jinbo Bi (University of Connecticut)

Density Constrained Reinforcement Learning
Zengyi Qin (MIT) · Yuxiao Chen (California Institute of Technology) · Chuchu Fan (MIT)

SPADE: A Spectral Method for Black-Box Adversarial Robustness Evaluation
Wuxinlin Cheng (Stevens Institute of Technology) · Chenhui Deng (Cornell University) · Zhiqiang Zhao (Stevens Institute of Technology) · Yaohui Cai (Cornell University) · Zhiru Zhang (Cornell Univeristy) · Zhuo Feng (Stevens Institute of Technology)

Learning Self-Modulating Attention in Continuous Time Space with Applications to Sequential Recommendation
Chao Chen (Shanghai Jiao Tong University) · Haoyu Geng (Shanghai Jiao Tong University) · Nianzu Yang (Shanghai Jiao Tong University) · Junchi Yan (Shanghai Jiao Tong University) · Daiyue Xue (Meituan) · Jianping Yu (Meituan) · Xiaokang Yang (Shanghai Jiao Tong University of China)

Decoupling Exploration and Exploitation for Meta-Reinforcement Learning without Sacrifices
Evan Liu (Stanford University) · Aditi Raghunathan (Stanford) · Percy Liang (Stanford University) · Chelsea Finn (Stanford)

Modeling Hierarchical Structures with Continuous Recursive Neural Networks
Jishnu Ray Chowdhury (University of Illinois at Chicago) · Cornelia Caragea (Computer Science, University of Illinois at Chicago)

CRPO: A New Approach for Safe Reinforcement Learning with Convergence Guarantee
Tengyu Xu (The Ohio State University) · Yingbin LIANG (The Ohio State University) · Guanghui Lan (Georgia Institute of Technology)

Generative Adversarial Transformers
Dor Arad (Stanford University) · Larry Zitnick (Facebook AI Research)

A Framework for Private Matrix Analysis in Sliding Window Model
Jalaj Upadhyay (Apple) · Sarvagya Upadhyay (Fujitsu Research America)

Nondeterminism and Instability in Neural Network Optimization
Cecilia Summers (University of Auckland) · Michael J Dinneen (University of Auckland)

Guarantees for Tuning the Step Size using a Learning-to-Learn Approach
Xiang Wang (Duke University) · Shuai Yuan (Duke University) · Chenwei Wu (Duke University) · Rong Ge (Duke University)

Bayesian Attention Belief Networks
Shujian Zhang (UT Austin) · Xinjie Fan (UT Austin) · Bo Chen (School of Electronic Engineering, Xidian University) · Mingyuan Zhou (University of Texas at Austin)

Large-Scale Multi-Agent Deep FBSDEs
Tianrong Chen (Georgia Institute of Technology) · Ziyi Wang (Georgia Institute of Technology) · Ioannis Exarchos (Stanford University) · Evangelos Theodorou (Georgia Tech)

Online Learning for Load Balancing of Unknown Monotone Resource Allocation Games
Ilai Bistritz (Stanford) · Nicholas Bambos (Stanford University)

Model-based Reinforcement Learning for Continuous Control with Posterior Sampling
Ying Fan (University of Wisconsin-Madison) · Yifei Ming (University of Wisconsin-Madison)

Defense against backdoor attacks via robust covariance estimation
Jonathan S Hayase (University of Washington) · Weihao Kong (University of Washington) · Raghav Somani (University of Washington) · Sewoong Oh (University of Washington)

GANMEX: One-vs-One Attributions using GAN-based Model Explainability
Sheng-Min Shih (AWS) · Pin-Ju Tien (NA) · Zohar Karnin (Amazon)

Quantifying the Benefit of Using Differentiable Learning over Tangent Kernels
Eran Malach (Hebrew University Jerusalem Israel) · Pritish Kamath (Toyota Technological Institute at Chicago) · Emmanuel Abbe () · Nati Srebro (Toyota Technological Institute at Chicago)

SAINT-ACC: Safety-Aware Intelligent Adaptive Cruise Control for Autonomous Vehicles Using Deep Reinforcement Learning
Lokesh Chandra Das (The University of Memphis) · Myounggyu Won (University of Memphis)

Quantifying Availability and Discovery in Recommender Systems via Stochastic Reachability
Mihaela Curmei (Berkeley) · Sarah Dean (UC Berkeley) · Benjamin Recht (Berkeley)

STRODE: Stochastic Boundary Ordinary Differential Equation
Huang Hengguan (NUS) · Hongfu Liu (National University of Singapore) · Hao Wang (Rutgers University) · Chang Xiao (National University of Singapore) · Ye Wang (National University of Singapore)

Exponential Reduction in Sample Complexity with Learning of Ising Model Dynamics
Arkopal Dutt (Massachusetts Institute of Technology) · Andrey Lokhov (Los Alamos National Laboratory) · Marc Vuffray (Los Alamos National Laboratory) · Sidhant Misra (Los Alamos National Laboratory)

Robust Reinforcement Learning using Least Squares Policy Iteration with Provable Performance Guarantees
Kishan Panaganti (TAMU) · Dileep Kalathil (TAMU)

Factor-analytic inverse regression for high-dimension, small-sample dimensionality reduction
Aditi Jha (Princeton University) · Michael J. Morais (Princeton University) · Jonathan Pillow (Princeton University)

Modularity in Reinforcement Learning via Algorithmic Independence in Credit Assignment
Michael Chang (UC Berkeley) · Sid Kaushik (UCB) · Sergey Levine (UC Berkeley) · Thomas Griffiths (Princeton University)

Quantile Bandits for Best Arms Identification
Mengyan Zhang (The Australian National University; Data61, CSIRO) · Cheng Soon Ong (Data61 and ANU)

Doubly Robust Off-Policy Actor-Critic: Convergence and Optimality
Tengyu Xu (The Ohio State University) · Zhuoran Yang (Princeton University) · Zhaoran Wang (Northwestern U) · Yingbin LIANG (The Ohio State University)

On the Generalization Power of Overfitted Two-Layer Neural Tangent Kernel Models
Peizhong Ju (Purdue University) · Xiaojun Lin (Purdue University) · Ness Shroff (The Ohio State University)

Compressed Maximum Likelihood
Yi Hao (University of California, San Diego) · Alon Orlitsky (UCSD)

Matrix Completion with Model-free Weighting
Jiayi Wang (Texas A&M University) · Raymond K. W. Wong (Texas A&M University) · Xiaojun Mao (Fudan University) · Kwun Chuen Gary Chan (University of Washington)

Improved Corruption Robust Algorithms for Episodic Reinforcement Learning
Yifang Chen (University of Washington) · Simon Du (University of Washington) · Kevin Jamieson (University of Washington)

Don’t Just Blame Over-parametrization for Over-confidence: Theoretical Analysis of Calibration in Binary Classification
Yu Bai (Salesforce Research) · Song Mei (UC Berkeley) · Huan Wang (Salesforce Research) · Caiming Xiong (Salesforce)

SpreadsheetCoder: Formula Prediction from Semi-structured Context
Xinyun Chen (UC Berkeley) · Petros Maniatis (Google Research) · Rishabh Singh (Google Brain) · Charles Sutton (Google) · Hanjun Dai (Google Brain) · Max Lin () · Denny Zhou (Google Brain)

Deep Generative Learning via Schrödinger Bridge
Gefei Wang (The Hong Kong University of Science and Technology) · Yuling Jiao (Zhongnan University of Ecomomics and Law) · Qian Xu (WeBank) · Yang Wang (HKUST) · Can Yang (HKUST)

Whitening and second order optimization both make information in the dataset unusable during training, and can reduce or prevent generalization
Neha Wadia (University of California, Berkeley) · Daniel Duckworth (Google Brain) · Samuel Schoenholz (Google Brain) · Ethan Dyer (Google) · Jascha Sohl-Dickstein (Google Brain)

Offline Meta-Reinforcement Learning with Advantage Weighting
Eric Mitchell (Stanford) · Rafael Rafailov (Stanford University) · Xue Bin Peng (UC Berkeley) · Sergey Levine (University of California, Berkeley) · Chelsea Finn (Stanford)

An End-to-End Framework for Molecular Conformation Generation via Bilevel Programming
Minkai Xu (University of Montreal) · Wujie Wang (Massachusetts Institute of Technology) · Shitong Luo (Peking University) · Chence Shi (University of Montreal) · Yoshua Bengio (Mila - Quebec AI Institute) · Rafael Gomez-Bombarelli (MIT) · Jian Tang (HEC Montreal & MILA)

Tesseract: Tensorised Actors for Multi-Agent Reinforcement Learning
Anuj Mahajan (Dept. of Computer Science, University of Oxford) · Mikayel Samvelyan (University College London) · Lei Mao (NVIDIA) · Viktor Makoviychuk (NVIDIA) · Animesh Garg (University of Toronto, Vector Institute, Nvidia) · Jean Kossaifi (NVIDIA) · Shimon Whiteson (University of Oxford) · Yuke Zhu (University of Texas - Austin) · Anima Anandkumar (Caltech and NVIDIA)

PID Accelerated Value Iteration Algorithm
Amir-massoud Farahmand (Vector Institute & University of Toronto) · Mohammad Ghavamzadeh (Google Research)

Byzantine-Resilient High-Dimensional SGD with Local Iterations on Heterogeneous Data
Deepesh Data (UCLA) · Suhas Diggavi (UCLA)

Active Learning for Distributionally Robust Level-Set Estimation
Yu Inatsu (Nagoya Institute of Technology) · Shogo Iwazaki (Nagoya Institute of Technology) · Ichiro Takeuchi (Nagoya Institute of Technology / RIKEN)

Incentivized Bandit Learning with Self-Reinforcing User Preferences
Tianchen Zhou (The Ohio State University) · Jia Liu (The Ohio State University) · Chaosheng Dong (Amazon) · jingyuan deng (amazon)

Quantization Algorithms for Random Fourier Features
Xiaoyun Li (Rutgers University) · Ping Li (Baidu)

Accelerating Gossip SGD with Periodic Global Averaging
Yiming Chen (Alibaba Group) · Kun Yuan (Alibaba Group (US)) · Yingya Zhang (Alibaba Group) · Pan Pan (Alibaba Group) · Yinghui Xu (Alibaba DAMO Academy) · Wotao Yin (Alibaba US, DAMO Academy)

SGA: A Robust Algorithm for Partial Recovery of Tree-Structured Graphical Models with Noisy Samples
Anshoo Tandon (National University of Singapore) · Aldric Han (National University of Singapore) · Vincent Tan (National University of Singapore)

Few-Shot Conformal Prediction with Auxiliary Tasks
Adam Fisch (MIT) · Tal Schuster (MIT CSAIL) · Tommi Jaakkola (MIT) · Regina Barzilay (MIT CSAIL)

Graph Convolution for Semi-Supervised Classification: Improved Linear Separability and Out-of-Distribution Generalization
Aseem Baranwal (University of Waterloo) · Kimon Fountoulakis (University of Waterloo) · Aukosh Jagannath (University of Waterloo)

Beyond $log^2(T)$ regret for decentralized bandits in matching markets
Soumya Basu (Google) · Karthik Abinav Sankararaman (Facebook) · Abishek Sankararaman (Amazon)

Uncovering the Connections Between Adversarial Transferability and Knowledge Transferability
Kaizhao Liang (University of Illinois, Urbana Champaign) · Jacky Zhang (University of Illinois at Urbana-Champaign) · Boxin Wang (University of Illinois at Urbana-Champaign) · Zhuolin Yang (University of Illinois at Urbana-Champaign) · Sanmi Koyejo (Illinois / Google) · Bo Li (UIUC)

Rethinking Neural vs. Matrix-Factorization Collaborative Filtering: the Theoretical Perspectives
Da Xu (Walmart Labs) · Chuanwei Ruan (Walmart Labs) · Evren Korpeoglu (Walmart Labs) · Sushant Kumar (Walmart Labs) · Kannan Achan (Walmart Labs)

Multi-layered Network Exploration via Random Walks: From Offline Optimization to Online Learning
Xutong Liu (The Chinese University of Hong Kong) · Jinhang Zuo (Carnegie Mellon University) · Xiaowei Chen (Bytedance) · Wei Chen (Microsoft) · John C. S. Lui (The Chinese University of Hong Kong)

Finding k in Latent $k-$ polytope
Chiranjib Bhattacharyya (Indian Institute of Science) · Ravindran Kannan (Microsoft Research India) · Amit Kumar (IIT Delhi)

Federated Learning of User Verification Models Without Sharing Embeddings
Hossein Hosseini (Qualcomm AI Research) · Hyunsin Park (Qualcomm AI Research) · Sungrack Yun (Qualcomm AI Research) · Christos Louizos (Qualcomm AI Research) · Joseph B Soriaga (Qualcomm Technologies, Inc.) · Max Welling (Qualcomm AI Research)

Efficient Online Learning for Dynamic k-Clustering
Stratis Skoulakis (Singapore University of Technology and Design) · Georgios Piliouras (Singapore University of Technology and Design) · Dimitris Fotakis (National Technical University of Athens)

Training Data Subset Selection for Regression with Controlled Validation Error
Durga S (Indian Institute of Technology Bombay) · Rishabh Iyer (University of Texas at Dallas) · Ganesh Ramakrishnan (IIT Bombay) · Abir De (IIT Bombay)

A Representation Learning Perspective on the Importance of Train-Validation Splitting in Meta-Learning
Nikunj Umesh Saunshi (Princeton University) · Arushi Gupta (Princeton University) · Wei Hu (Princeton University)

Single Pass Entrywise-Transformed Low Rank Approximation
Yifei Jiang (Tianjin University) · Yi Li (Nanyang Technological University) · Yiming Sun (Nanyang Technological University) · Jiaxin Wang (Wuhan University of Technology) · David Woodruff (Carnegie Mellon University)

Which transformer architecture fits my data? A vocabulary bottleneck in self-attention
Noam Wies (The Hebrew University of Jerusalem) · Yoav Levine (HUJI) · Daniel Jannai (Hebrew University of Jerusalem) · Amnon Shashua ((The Hebrew University of Jerusalem, IL))

Automatic RNN Repair via Model-based Analysis
Xiaofei Xie (Nanyang Technological University) · Wenbo Guo (Pennsylvania State University) · Lei Ma (University of Alberta) · Wei Le (Iowa State University) · Jian Wang (Nanyang Technological University) · Lingjun Zhou (College of Intelligence and Computing,Tianjin University) · Yang Liu (Nanyang Technology University, Singapore) · Xinyu Xing (The Pennsylvania State University)

Implicit Regularization in Tensor Factorization
Noam Razin (Tel Aviv University) · Asaf Maman (Tel Aviv University) · Nadav Cohen (Tel Aviv University)

Autoencoder Image Interpolation by Shaping the Latent Space
Alon Oring (IDC) · Zohar Yakhini (Herzliya Interdisciplinary Center) · Yacov Hel-Or (The Interdisciplinary Center, Herzliya)

SagaNet: A Small Sample Gated Network for Pediatric Cancer Diagnosis
Yuhan Liu (East China Normal University) · Shiliang Sun (East China Normal University)

GBHT: Gradient Boosting Histogram Transform for Density Estimation
Jingyi Cui (Peking University) · Hanyuan Hang (University of Twente) · Yisen Wang (Peking University) · Zhouchen Lin (Peking University)

Distributed Nystr\"{o}m Kernel Learning with Communications
Rong Yin (Institute of Information Engineering, CAS; School of Cyber Security, University of Chinese Academy of Sciences) · Weiping Wang (Institute of Information Engineering, CAS, China) · Dan Meng (Institute of Information Engineering, CAS)

Catastrophic Fisher Explosion: Early Phase Fisher Matrix Impacts Generalization
Stanislaw Jastrzebski (New York University) · Devansh Arpit (Salesforce Research) · Oliver Astrand (.) · Giancarlo Kerg (MILA) · Huan Wang (Salesforce Research) · Caiming Xiong (Salesforce) · Richard Socher (Salesforce) · Kyunghyun Cho (New York University) · Krzysztof J Geras (New York University)

PEBBLE: Feedback-Efficient Interactive Reinforcement Learning via Relabeling Experience and Unsupervised Pre-training
Kimin Lee (UC Berkeley) · Laura Smith (UC Berkeley) · Pieter Abbeel (UC Berkeley & Covariant)

Recomposing the Reinforcement Learning Building Blocks with Hypernetworks
Elad Sarafian (Bar-Ilan University) · Shai Keynan (Bar Ilan University) · Sarit Kraus (Bar-Ilan University)

Almost Optimal Anytime Algorithm for Batched Multi-Armed Bandits
Tianyuan Jin (National University of Singapore) · Jing Tang (The Hong Kong University of Science and Technology) · Pan Xu (California Institute of Technology) · Keke Huang (National University of Singapore) · Xiaokui Xiao (National University of Singapore) · Quanquan Gu (University of California, Los Angeles)

Bias-Robust Bayesian Optimization via Dueling Bandits
Johannes Kirschner (ETH Zurich) · Andreas Krause (ETH Zurich)

Fast Algorithms for Stackelberg Prediction Game with Least Squares Loss
jiali wang (fudan university) · He Chen (Fudan University) · Rujun Jiang (Fudan University) · Xudong Li (Fudan University) · Zihao Li (Fudan University)

PODS: Policy Optimization via Differentiable Simulation
Miguel Angel Zamora Mora (ETH Zurich) · Momchil Peychev (ETH Zurich) · Sehoon Ha (Georgia Institute of Technology) · Martin Vechev (ETH Zurich) · Stelian Coros (ETH Zurich)

Equivariant message passing for the prediction of tensorial properties and molecular spectra
Kristof T Schütt (Technische Universität Berlin) · Oliver Unke (Technische Universität Berlin) · Michael Gastegger (TU Berlin)

Efficient Generative Modelling of Protein Structure Fragments using a Deep Markov Model
Christian Thygesen (University of Copenhagen) · Christian Skjødt Steenmans (Evaxion Biotech) · Ahmad Salim Al-Sibahi (University of Copenhagen) · Lys Sanz Moreta (University of Copenhagen) · Anders Bundgård Sørensen (Evaxion Biotech) · Thomas Hamelryck (University of Copenhagen)

Light RUMs
Flavio Chierichetti (Sapienza University) · Ravi Kumar (Google) · Andrew Tomkins (Google)

Homomorphic Sensing: Sparsity and Noise
Liangzu Peng (ShanghaiTech University) · Boshi Wang (ShanghaiTech University) · Manolis Tsakiris (ShanghaiTech University)

Bootstrapping Fitted Q-Evaluation for Off-Policy Inference
Botao Hao (Princeton University) · Xiang Ji (Princeton University) · Yaqi Duan (Princeton University) · Hao Lu (Princeton University) · Csaba Szepesvari (DeepMind/University of Alberta) · Mengdi Wang (Princeton University)

Concentric mixtures of Mallows models for top-$k$ rankings: sampling and identifiability
Fabien Collas (BCAM) · Ekhine IRUROZKI (Telecom Paris)

Differentially Private Aggregation in the Shuffle Model: Almost Central Accuracy in Almost a Single Message
Badih Ghazi (Google) · Ravi Kumar (Google) · Pasin Manurangsi (Google Research) · Rasmus Pagh (University of Copenhagen) · Amer Sinha (Google)

Sparse Feature Selection Makes Batch Reinforcement Learning More Sample Efficient
Botao Hao (Princeton University) · Yaqi Duan (Princeton University) · Tor Lattimore (DeepMind) · Csaba Szepesvari (DeepMind/University of Alberta) · Mengdi Wang (Princeton University)

Locally Private k-Means in One Round
Alisa Chang (Google) · Badih Ghazi (Google) · Ravi Kumar (Google) · Pasin Manurangsi (Google Research)

Solving Challenging Dexterous Manipulation Tasks With Trajectory Optimisation and Reinforcement Learning
Henry Charlesworth (University of Warwick) · Giovanni Montana (University of Warwick)

Learning Gradient Fields for Molecular Conformation Generation
Chence Shi (University of Montreal) · Shitong Luo (Peking University) · Minkai Xu (University of Montreal) · Jian Tang (HEC Montreal & MILA)

Optimization Planning for 3D ConvNets
Zhaofan Qiu (JD.com) · Ting Yao (JD AI Research) · Chong-Wah Ngo (Singapore Management University) · Tao Mei (AI Research of JD.com)

BANG: Bridging Autoregressive and Non-autoregressive Generation with Large Scale Pretraining
Weizhen Qi (University of Science and Technology of China) · Yeyun Gong (Microsoft Research Asia) · Jian Jiao (Microsoft) · Yu Yan (Microsoft) · Weizhu Chen (Microsoft) · Dayiheng Liu (Alibaba DAMO Academy) · Kewen Tang (Microsoft) · Houqiang Li (University of Science and Technology of China) · Jiusheng Chen (Microsoft) · Ruofei Zhang (Microsoft) · Ming Zhou (Microsoft Research) · Nan Duan (Microsoft Research)

ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases
Stéphane d'Ascoli (ENS / FAIR, Paris) · Hugo Touvron (Facebook AI Research) · Matthew Leavitt (Facebook AI Research (FAIR)) · Ari Morcos (Facebook AI Research (FAIR)) · Giulio Biroli (ENS) · Levent Sagun ()

Monte Carlo Variational Auto-Encoders
Achille Thin (Ecole polytechnique) · Nikita Kotelevskii (Skolkovo Institute of Science and Technology) · Arnaud Doucet (Oxford University) · Alain Durmus (ENS Paris Saclay) · Eric Moulines (Ecole Polytechnique) · Maxim Panov (Skolkovo Institute of Science and Technology)

Meta-Learning Gradient-Free Bidirectional Networks
Mark Sandler (Google) · Andrey Zhmoginov (Google Inc.) · Max Vladymyrov (Google) · Nolan Miller (Google) · Tom Madams (Google) · Andrew Jackson (Google) · Blaise Agüera y Arcas (Google)

Unsupervised Skill Discovery with Bottleneck Option Learning
Jaekyeom Kim (Seoul National University) · Seohong Park (Seoul National University) · Gunhee Kim (Seoul National University)

One-sided Frank-Wolfe algorithms for saddle problems
Vladimir Kolmogorov (Institute of Science and Technology, Austria) · Thomas Pock (Graz University of Technology)

Classifying high-dimensional Gaussian mixtures: Where kernel methods fail and neural networks succeed
Maria Refinetti (Laboratoire de Physique de l’Ecole Normale Supérieure Paris) · Sebastian Goldt (International School of Advanced Studies (SISSA)) · FLORENT KRZAKALA (EPFL) · Lenka Zdeborova (EPFL)

Lipschitz normalization for self-attention layers with application to graph neural networks
George Dasoulas (Ecole Polytechnique, Paris, France) · Kevin Scaman (Noah's Ark, Huawei Technologies) · Aladin Virmaux (Huawei)

Patterns of Neural Activation
Jonas Fischer (Max Planck Institute for Informatics) · Anna Olah (Max Planck Institute for Informatics) · Jilles Vreeken (CISPA Helmholtz Center for Information Security)

Fast active learning for pure exploration in reinforcement learning
Pierre MENARD (Inria) · Omar Darwiche Domingues (Inria) · Anders Jonsson (Universitat Pompeu Fabra) · Emilie Kaufmann (CNRS, Univ. Lille) · Edouard Leurent () · Michal Valko (DeepMind / Inria / ENS Paris-Saclay)

BasisDeVAE: Interpretable Simultaneous Dimensionality Reduction and Feature-Level Clustering with Derivative-Based Variational Autoencoders
Dominic Danks (Alan Turing Institute) · Christopher Yau (University of Manchester)

Low-Rank Sinkhorn Factorization
Meyer Scetbon (CREST, ENSAE) · Marco Cuturi (Google) · Gabriel Peyré (CNRS and ENS)

More Powerful and General Selective Inference for Stepwise Feature Selection using Homotopy Method
Kazuya Sugiyama (Nagoya Institute of Technology) · Vo Nguyen Le Duy (Nagoya Institute of Technology / RIKEN) · Ichiro Takeuchi (Nagoya Institute of Technology / RIKEN)

Online Graph Dictionary Learning
Cédric Vincent-Cuaz (INRIA Sophia Antipolis) · Titouan Vayer (IRISA) · Rémi Flamary (École Polytechnique) · Marco Corneli (Université Côte d'Azur) · Nicolas Courty (UBS)

Think Global and Act Local: Bayesian Optimisation over High-Dimensional Categorical and Mixed Search Spaces
Xingchen Wan (University of Oxford) · Vu Nguyen (Amazon Adelaide) · Huong Ha (RMIT University) · Binxin Ru (University of Oxford) · Cong Lu (University of Oxford) · Michael A Osborne (U Oxford)

Approximation Theory Based Methods for RKHS Bandits
Sho Takemori (FUJIFILM Business Innovation) · Masahiro Sato (FUJIFILM Business Innovation)

Unbalanced minibatch Optimal Transport; applications to Domain Adaptation
Kilian Fatras (IRISA/INRIA) · Thibault Séjourné (Ecole Normale Supérieure) · Rémi Flamary (École Polytechnique) · Nicolas Courty (UBS)

Differentiable Particle Filtering via Entropy-Regularized Optimal Transport
Adrien Corenflos (Aalto University) · James Thornton (University of Oxford) · George Deligiannidis (Oxford) · Arnaud Doucet (Oxford University)

On Characterizing GAN Convergence Through Proximal Duality Gap
Sahil Sidheekh (Indian Institute of Technology Ropar) · Aroof Aimen (Indian Institute of Techology, Ropar) · Narayanan Chatapuram Krishnan (Indian Institute of Technology Ropar)

UCB Momentum Q-learning: Correcting the bias without forgetting
Pierre MENARD (Inria) · Omar Darwiche Domingues (Inria) · Xuedong Shang (Inria) · Michal Valko (DeepMind / Inria / ENS Paris-Saclay)

Training Adversarially Robust Sparse Networks via Bayesian Connectivity Sampling
Ozan Özdenizci (Graz University of Technology) · Robert Legenstein (Graz University of Technology)

Continuous-time Model-based Reinforcement Learning
Cagatay Yildiz (Aalto University) · Markus Heinonen (Aalto University) · Harri Lähdesmäki (Aalto University)

Differentially-Private Clustering of Easy Instances
Edith Cohen (Google Research and Tel Aviv University) · Haim Kaplan (TAU, GOOGLE) · Yishay Mansour (Google and Tel Aviv University) · Uri Stemmer (Ben-Gurion University) · Eliad Tsfadia (Tel Aviv University and Google Research)

Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech
Vadim Popov (Huawei Noah's Ark Lab) · Ivan Vovk (Huawei Noah's Ark Lab; Higher School of Economics) · Vladimir Gogoryan (Huawei Noah's Ark Lab; Higher School of Economics) · Tasnima Sadekova (Huawei Noah's Ark Lab) · Mikhail Kudinov (Huawei Noah's Ark Lab)

Policy Information Capacity: Information-Theoretic Measure for Task Complexity in Deep Reinforcement Learning
Hiroki Furuta (The University of Tokyo) · Tatsuya Matsushima (The University of Tokyo) · Tadashi Kozuno (University of Alberta) · Yutaka Matsuo (University of Tokyo) · Sergey Levine (UC Berkeley) · Ofir Nachum (Google Brain) · Shixiang Gu (Google)

Kernel-Based Reinforcement Learning: A Finite-Time Analysis
Omar Darwiche Domingues (Inria) · Pierre Menard (Inria) · Matteo Pirotta (Facebook AI Research) · Emilie Kaufmann (CNRS, Univ. Lille) · Michal Valko (DeepMind / Inria / ENS Paris-Saclay)

Model Distillation for Revenue Optimization: Interpretable Personalized Pricing
Max Biggs (University of Virginia) · Wei Sun (IBM Research) · Markus Ettl (IBM Research)

Breaking the Limits of Message Passing Graph Neural Networks
Muhammet Balcilar (Université de Rouen Normandie - LITIS) · Pierre Heroux (University of Rouen Normandy) · Benoit Gauzere (INSA Rouen) · Pascal Vasseur (Université de Picardie Jules Verne) · Sebastien Adam (Université de Rouen Normandie) · Paul Honeine (LITIS Lab, Université de Rouen Normandie)

Toward Understanding the Feature Learning Process of Self-supervised Contrastive Learning
Zixin Wen (UIBE) · Yuanzhi Li (CMU)

Robust Learning-Augmented Caching: An Experimental Study
Jakub Chłędowski (Jagiellonian University) · Adam Polak (École Polytechnique Fédérale de Lausanne) · Bartosz Szabucki (Jagiellonian University) · Konrad Zolna (DeepMind, Jagiellonian University)

Scaling Multi-Agent Reinforcement Learning with Selective Parameter Sharing
Filippos Christianos (University of Edinburgh) · Georgios Papoudakis (The University of Edinburgh) · Muhammad Arrasy Rahman (The University of Edinburgh) · Stefano Albrecht (University of Edinburgh)

Domain Generalization using Causal Matching
Divyat Mahajan (Microsoft Research India) · Shruti Tople (Microsoft Research) · Amit Sharma (Microsoft Research)

From Local to Global Norm Emergence: Dissolving Self-reinforcing Substructures with Incremental Social Instruments
Yiwei Liu (Beijing Institute of Technology) · Jiamou Liu (The University of Auckland) · Kaibin Wan (Beijing Institute of Technology) · Zhan Qin (Zhejiang University) · Zijian Zhang (Beijing Institute of Technology) · Bakhadyr Khoussainov (The University of Auckland) · Liehuang Zhu (Beijing Institute of Technology)

Towards Open Ad Hoc Teamwork Using Graph-based Policy Learning
Muhammad Arrasy Rahman (The University of Edinburgh) · Niklas Hopner (University of Amsterdam) · Filippos Christianos (University of Edinburgh) · Stefano Albrecht (University of Edinburgh)

A Novel Method to Solve Neural Knapsack Problems
Duanshun Li (University of Alberta) · Jing Liu (Walmart Research Lab.) · Dongeun Lee (Texas A&M University-Commerce) · Ali Seyedmazloom (George Mason Univeristy) · Giridhar Kaushik (George Mason Univeristy) · Kookjin Lee (Arizona State University) · Noseong Park (Yonsei University, Korea)

Self Normalizing Flows
T. Anderson Keller (University of Amsterdam) · Jorn Peters (University of Amsterdam) · Priyank Jaini (University of Amsterdam) · Emiel Hoogeboom (University of Amsterdam) · Patrick Forré (University of Amsterdam) · Max Welling (University of Amsterdam & Qualcomm)

From Local Structures to Size Generalization in Graph Neural Networks
Gilad Yehudai (Weizmann Institute of Science) · Ethan Fetaya (Bar-Ilan University) · eli meirom (NVIDIA) · Gal Chechik (Nvidia) · Haggai Maron (NVIDIA Research)

LAMDA: Label Matching Deep Domain Adaptation
Trung Le (Monash University) · Tuan Nguyen (Monash University) · Nhat Ho (University of Texas at Austin) · Hung Bui (VinAI Research) · Dinh Phung (Monash University, Australia)

HoroPCA: Hyperbolic Dimensionality Reduction via Horospherical Projections
Ines Chami (Stanford University) · Albert Gu (Stanford University) · Dat P Nguyen (Stanford University) · Christopher Re (Stanford)

Approximate Group Fairness for Clustering
Bo Li (Department of Computing The Hong Kong Polytechnic University) · Lijun Li (Ocean University of China) · Ankang Sun (Warwick Business School, the University of Warwick) · Chenhao Wang (City University of Hong Kong) · Yingfan Wang (Department of Computer Science, Duke University)

Estimating Identifiable Causal Effects on Markov Equivalence Class through Double Machine Learning
Yonghan Jung (Purdue University) · Jin Tian (Iowa State University) · Elias Bareinboim (Columbia)

Differentially Private Sliced Wasserstein Distance
alain rakotomamonjy (Universite de Rouen Normandie / Criteo AI Lab) · Ralaivola Liva (Criteo AI Lab)

K-shot NAS: Learnable Weight-Sharing for NAS with K-shot Supernets
Xiu Su (University of Sydney) · Shan You (SenseTime Research) · Mingkai Zheng (SenseTime) · Fei Wang (SenseTime) · Chen Qian (SenseTime) · Changshui Zhang (Tsinghua University) · Chang Xu (University of Sydney)

Towards Better Robust Generalization with Shift Consistency Regularization
Shufei Zhang (University of Liverpool) · Zhuang Qian (Xi'an Jiaotong-Liverpool University) · Kaizhu Huang (Xi'an Jiaotong-Liverpool Univ.) · Qiufeng Wang (Xi'an Jiaotong-Liverpool University) · Rui Zhang (Xi'an Jiaotong-Liverpool University) · Xinping Yi (University of Liverpool)

Phase Transitions, Distance Functions, and Implicit Neural Representations
Yaron Lipman (Facebook AI Research)

Zeroth-Order Non-Convex Learning via Hierarchical Dual Averaging
Amélie Héliou (Criteo) · Matthieu Martin (Criteo AI Lab) · Panayotis Mertikopoulos (CNRS and Criteo AI Lab) · Thibaud J Rahier (INRIA)

Discriminative Complementary-Label Learning with Weighted Loss
Yi Gao (Southeast University) · Min-Ling Zhang (Southeast University)

Not All Memories are Created Equal: Learning to Forget by Expiring
Sainbayar Sukhbaatar (Facebook AI Research) · Da JU (Facebook AI Research) · Spencer Poff (Facebook) · Stephen Roller (Facebook) · Arthur Szlam (Facebook) · Jason Weston (FAIR) · Angela Fan (Facebook AI Research)

Sequential Domain Adaptation by Synthesizing Distributionally Robust Experts
Bahar Taskesen (EPFL) · Man Chung Yue (Hong Kong Polytechnic University) · Jose Blanchet (Stanford University) · Daniel Kuhn (EPFL) · Viet Anh Nguyen (Stanford University / VinAI Research)

Adversarial Purification with Score-based Generative Models
Jongmin Yoon (KAIST) · Sung Ju Hwang (KAIST, AITRICS) · Juho Lee (KAIST, AITRICS)

Newton Method over Networks is Fast up to the Statistical Precision
Amir Daneshmand (Purdue University) · Gesualdo Scutari (Purdue) · Pavel Dvurechenskii (Weierstrass Institute) · Alexander Gasnikov (Moscow Institute of Physics and Technology)

Self-Improved Retrosynthetic Planning
Junsu Kim (KAIST) · Sungsoo Ahn (MBZUAI) · Hankook Lee (KAIST) · Jinwoo Shin (KAIST)

Data-efficient Hindsight Off-policy Option Learning
Markus Wulfmeier (DeepMind) · Dushyant Rao (DeepMind) · Roland Hafner (DeepMind) · Thomas Lampe (DeepMind) · Abbas Abdolmaleki (DeepMind) · Tim Hertweck (DeepMind) · Michael Neunert (Google DeepMind) · Dhruva Tirumala Bukkapatnam (DeepMind) · Noah Siegel (DeepMind) · Nicolas Heess (DeepMind) · Martin Riedmiller (DeepMind)

A New Representation of Successor Features for Transfer across Dissimilar Environments
Majid Abdolshah (Deakin University) · Sunil Gupta (Deakin University) · Santu Rana (Deakin University) · Hung Le (Deakin University) · Thommen Karimpanal George (Deakin University) · Svetha Venkatesh (Deakin University)

A Gradient Based Strategy for Hamiltonian Monte Carlo Hyperparameter Optimization
Andrew Campbell (University of Oxford) · Wenlong Chen (Baidu Inc.) · Vincent Stimper (University of Cambridge) · Jose Miguel Hernandez-Lobato (University of Cambridge) · Yichuan Zhang (Boltzbit Limited)

GNNAutoScale: Scalable and Expressive Graph Neural Networks via Historical Embeddings
Matthias Fey (TU Dortmund University) · Jan Eric Lenssen (TU Dortmund) · Frank Weichert (Technical University of Dortmund) · Jure Leskovec (Stanford University)

Improving Gradient Regularization using Complex-Valued Neural Networks
Eric Yeats (Duke University) · Yiran Chen (Duke University) · Hai Li (Duke University)

The Hintons in your Neural Network: a Quantum Field Theory View of Deep Learning
Roberto Bondesan (Qualcomm AI Research) · Max Welling (Qualcomm AI Research)

Function Contrastive Learning of Transferable Meta-Representations
Muhammad Waleed Gondal (Max Planck Institute for Intelligent Systems) · Shruti Joshi (MPI for Intelligent Systems, Tübingen) · Nasim Rahaman (Max Planck Institute for Intelligent Systems) · Stefan Bauer (Max Planck Institute for Intelligent Systems) · Manuel Wuthrich (Max Planck Institute for Intelligent Systems) · Bernhard Schölkopf (MPI for Intelligent Systems Tübingen, Germany)

Architectural Universality Of Neural Tangent Kernel Training Dynamics
Greg Yang (Microsoft Research) · Etai Littwin (Apple)

A Novel Sequential Coreset Method for Gradient Descent Algorithms
Jiawei Huang (University of Science and Technology of China) · Ruomin Huang (University of Science and Technology of China) · wenjie liu (University of Science and Technology of China) · Nikolaos Freris (University of Science and Technology of China) · Hu Ding (University of Science and Technology of China)

Muesli: Combining Improvements in Policy Optimization
Matteo Hessel (DeepMind) · Ivo Danihelka (DeepMind) · Fabio Viola (DeepMind) · Arthur Guez (Google DeepMind) · Simon Schmitt (DeepMind) · Laurent Sifre (DeepMind) · Theophane Weber (DeepMind) · David Silver (Google DeepMind) · Hado van Hasselt (DeepMind)

Leveraging Sparse Linear Layers for Debuggable Deep Networks
Eric Wong (MIT) · Shibani Santurkar (MIT) · Aleksander Madry (MIT)

Partially Observed Exchangeable Modeling
Yang Li (University of North Carolina at Chapel Hill) · Junier Oliva (UNC-Chapel Hill)

Active Feature Acquisition with Generative Surrogate Models
Yang Li (University of North Carolina at Chapel Hill) · Junier Oliva (UNC-Chapel Hill)

Multi-group Agnostic PAC Learnability
Guy Rothblum (Weizmann Institute of Science) · Gal Yona (Weizmann Institute of Science)

Annealed Flow Transport Monte Carlo
Michael Arbel (University College London) · Alexander Matthews (DeepMind) · Arnaud Doucet (Google DeepMind)

Active Slices for Sliced Stein Discrepancy
Wenbo Gong (University of Cambridge) · Kaibo Zhang (University of Cambridge) · Yingzhen Li (Imperial College London) · Jose Miguel Hernandez-Lobato (University of Cambridge)

UnICORNN: A recurrent model for learning very long time dependencies
T. Konstantin Rusch (ETH Zurich) · Siddhartha Mishra (ETH Zurich)

Clustered Sampling: Low-Variance and Improved Representativity for Clients Selection in Federated Learning
Yann Fraboni (Accenture) · Richard Vidal (Accenture) · Laetitia Kameni (Accenture) · Marco Lorenzi (Inria UCA,)

Connecting Sphere Manifolds Hierarchically for Regularization
Damien Scieur (Samsung - SAIT AI Lab, Montreal) · Youngsung Kim (Samsung Advanced Institute of Technology)

Dual Principal Component Pursuit for Robust Subspace Learning: Theory and Algorithms for a Holistic Approach
Tianyu Ding (Johns Hopkins University) · Zhihui Zhu (Johns Hopkins University) · Rene Vidal (Johns Hopkins University, USA) · Daniel Robinson (Lehigh University)

ConvexVST: A Convex Optimization Approach to Variance-stabilizing Transformation
Mengfan Wang (Virginia Tech) · Boyu Lyu (Virginia Tech) · Guoqiang Yu (Virginia Tech)

Fair Classification with Noisy Protected Attributes: A Framework with Provable Guarantees
L. Elisa Celis (EPFL) · Lingxiao Huang (Tsinghua University) · Vijay Keswani (Yale University) · Nisheeth Vishnoi (Yale University)

Directional Bias Amplification
Angelina Wang (Princeton University) · Olga Russakovsky (Princeton University)

Local Graph Algorithms for Learning Higher-Order Structures
Peter Macgregor (University of Edinburgh) · He Sun (University of Edinburgh)

Learning Deep Neural Networks under Agnostic Corrupted Supervision
Boyang Liu (Michigan State University) · Mengying Sun (Michigan State University) · Ding Wang (Michigan State University) · Pang-Ning Tan (Michigan State University) · Jiayu Zhou (Michigan State University)

Sharing Less is More: Lifelong Learning in Deep Networks with Selective Layer Transfer
Seungwon Lee (University of Pennsylvania) · Sima Behpour (Carnegie Mellon University) · Eric Eaton (University of Pennsylvania)

Multi-Dimensional Classification via Sparse Label Encoding
BINBIN JIA (Southeast University) · Min-Ling Zhang (Southeast University)

SigGPDE: Scaling Sparse Gaussian Processes on Sequential Data
Maud Lemercier (University of Warwick) · Cristopher Salvi (University of Oxford) · Thomas Cass (Imperial College London) · Edwin Bonilla (CSIRO's Data61) · Theodoros Damoulas (University of Warwick & The Alan Turing Institute) · Terry Lyons (University of Oxford)

Hyperparameter Selection for Imitation Learning
Léonard Hussenot (Google Research, Brain Team) · Marcin Andrychowicz (Google) · Damien Vincent (Google Brain) · Robert Dadashi (Google Research) · Anton Raichuk (Google) · Sabela Ramos (Google Research) · Nikola Momchev (Google) · Sertan Girgin (Google Brain) · Raphael Marinier (Google) · Lukasz Stafiniak (Google) · Emmanuel Orsini (Google Brain) · Olivier Bachem (Google Brain) · Matthieu Geist (Google) · Olivier Pietquin (GOOGLE BRAIN)

Provably Efficient Learning of Transferable Rewards
Alberto Maria Metelli (Politecnico di Milano) · Giorgia Ramponi (Politecnico di Milano) · Alessandro Concetti (Politecnico di Milano) · Marcello Restelli (Politecnico di Milano)

Run-Sort-ReRun: Escaping Batch Size Limitations in Sliced Wasserstein Generative Models
José Lezama (Universidad de la República, Uruguay) · Wei Chen (Purdue University) · Qiang Qiu (Purdue University)

Ditto: Fair and Robust Federated Learning Through Personalization
Tian Li (Carnegie Mellon University) · Shengyuan Hu (Carnegie Mellon University) · Ahmad Beirami (Facebook AI) · Virginia Smith (Carnegie Mellon University)

Loss Surface Simplexes for Mode Connecting Volumes and Fast Ensembling
Gregory Benton (New York University) · Wesley Maddox (New York University) · Sanae Lotfi (New York University) · Andrew Wilson (New York University)

Parallel Droplet Control in MEDA Biochips using Multi-Agent Reinforcement Learning
Tung-Che Liang (Duke University) · Jin Zhou (Duke University) · Yun-Sheng Chan (National Chiao Tung University) · Tsung-Yi Ho (National Tsing Hua University) · Krishnendu Chakrabarty (Duke University) · Cy Lee (National Chiao Tung University)

Bias-Free Scalable Gaussian Processes via Randomized Truncations
Andres Potapczynski (Columbia University) · Luhuan Wu (Columbia University) · Dan Biderman (Columbia University) · Geoff Pleiss (Columbia University) · John Cunningham (Columbia University)

Consistent regression when oblivious outliers overwhelm
Tommaso d'Orsi (ETH Zurich) · Gleb Novikov (ETH Zurich) · David Steurer (ETH Zurich)

Submodular Maximization subject to a Knapsack Constraint: Combinatorial Algorithms with Near-optimal Adaptive Complexity
Georgios Amanatidis (University of Essex) · Federico Fusco (Sapienza University of Rome) · Philip Lazos (Sapienza University of Rome) · Stefano Leonardi (Sapienza University of Rome) · Alberto Marchetti-Spaccamela (Sapienza University of Rome) · Rebecca Reiffenhäuser (Sapienza University of Rome)

Better Training using Weight-Constrained Stochastic Dynamics
Benedict Leimkuhler (University of Edinburgh) · Tiffany Vlaar (University of Edinburgh) · Timothée Pouchon (University of Edinburgh) · Amos Storkey (University of Edinburgh)

Learning a Universal Template for Few-shot Dataset Generalization
Eleni Triantafillou (University of Toronto, Vector Institute) · Hugo Larochelle (Google Brain) · Richard Zemel (Vector Institute) · Vincent Dumoulin (Google)

Linear Transformers Are Secretly Fast Weight Memory Systems
Imanol Schlag (IDSIA) · Kazuki Irie (IDSIA) · Jürgen Schmidhuber (Swiss AI Lab)

Composed Fine-Tuning: Mitigating the Loss of Pre-Trained Output Structure
Sang Michael Xie (Stanford University) · Tengyu Ma (Stanford University) · Percy Liang (Stanford University)

Unsupervised Part Representation by Flow Capsules
Sara Sabour Rouh Aghdam (Google) · Andrea Tagliasacchi (Google Inc.) · Soroosh Yazdani (Google Inc.) · Geoffrey Hinton (Google) · David Fleet (University of Toronto)

Active Deep Probabilistic Subsampling
Hans van Gorp (Eindhoven University of Technology) · Iris Huijben (Eindhoven University of Technology) · Bastiaan Veeling (University of Amsterdam) · Nicola Pezzotti (Philips) · Ruud J. G. van Sloun (Technical university of Eindhoven)

Watermarking Deep Neural Networks with Greedy Residuals
Hanwen Liu (Peking University) · Zhenyu Weng (Peking University Shenzhen Graduate School) · Yuesheng Zhu (Peking University Shenzhen Graduate School)

Reinforcement Learning for Cost-Aware Markov Decision Processes
Wesley Suttle (Stony Brook University) · Kaiqing Zhang (University of Illinois at Urbana-Champaign/MIT) · Zhuoran Yang (Princeton University) · Ji Liu (Stony Brook University) · David N Kraemer (Stony Brook University)

Modelling Behavioural Diversity for Learning in Open-Ended Games
Nicolas Perez-Nieves (Imperial College London) · Yaodong Yang (Huawei UK) · Oliver Slumbers (UCL) · David Mguni (Noah's Ark Laboratory, Huawei) · Ying Wen (Shanghai Jiao Tong University) · Jun Wang (UCL)

Cumulants of Hawkes Processes are Robust to Observation Noise
William Trouleau (EPFL) · Jalal Etesami (Bosch Research Center for AI, Germany) · Matthias Grossglauser (EPFL) · Negar Kiyavash (École Polytechnique Fédérale de Lausanne) · Patrick Thiran (EPFL)

Environment Inference for Invariant Learning
Elliot Creager (University of Toronto) · Joern-Henrik Jacobsen (Apple Inc.) · Richard Zemel (Vector Institute)

Low-Precision Reinforcement Learning: Running Soft Actor-Critic in Half Precision
Johan Björck (Cornell) · Xiangyu Chen (Cornell University) · Christopher De Sa (Cornell) · Carla Gomes (Cornell University) · Kilian Weinberger (Cornell University)

Preferential Temporal Difference Learning
Nishanth Anand (Mila / McGill University) · Doina Precup (McGill University / DeepMind)

Discretization Drift in Two-Player Games
Mihaela Rosca (DeepMind, UCL) · Yan Wu (DeepMind) · Benoit Dherin (Google) · David GT Barrett (DeepMind)

A Probabilistic Approach to Neural Network Pruning
Xin Qian (Northwestern University) · Diego Klabjan (Northwestern University)

Quasi-global Momentum: Accelerating Decentralized Deep Learning on Heterogeneous Data
Tao Lin (EPFL) · Sai Praneeth Reddy Karimireddy (EPFL) · Sebastian Stich (EPFL) · Martin Jaggi (EPFL)

TeachMyAgent: a Benchmark for Automatic Curriculum Learning in Deep RL
Clément Romac (Inria) · Rémy Portelas (Inria Bordeaux - Sud-Ouest) · Katja Hofmann (Microsoft) · Pierre-Yves Oudeyer (Inria)

Improving Molecular Graph Neural Network Explainability with Orthonormalization and Induced Sparsity
Ryan Henderson (Bayer) · Djork-Arné Clevert (Bayer AG) · Floriane Montanari (Bayer AG)

Scalable Normalizing Flows for Symmetric Densities
Marin Biloš (Technical University of Munich) · Stephan Günnemann (Technical University of Munich)

Correcting Exposure Bias for Link Recommendation
Shantanu Gupta (Carnegie Mellon University) · Hao Wang (Rutgers University) · Zachary Lipton (Carnegie Mellon University) · Yuyang Wang (AWS AI Labs)

Neural Transformation Learning for Deep Anomaly Detection Beyond Images
Chen Qiu (TU Kaiserslautern/Bosch Center for Artificial Intelligence) · Timo Pfrommer (Bosch Center for Artificial Intelligence) · Marius Kloft (TU Kaiserslautern) · Stephan Mandt (University of California, Irivine) · Maja Rudolph (BCAI)

Geometry of the Loss Landscape in Overparameterized Neural Networks: Symmetries and Invariances
berfin simsek (EPFL) · François Ged (Ecole Polytechnique de Lausann) · Francesco Spadaro (EPFL) · Arthur Jacot (EPFL Lausanne Switzerland) · Clement Hongler (EPFL) · Johanni Brea (EPFL) · Wulfram Gerstner (EPFL)

Statistical Estimation from Dependent Data
Vardis Kandiros (MIT) · Yuval Dagan (MIT) · Nishanth Dikkala (Google Research) · Surbhi Goel (Microsoft Research) · Constantinos Daskalakis (MIT)

What Are Bayesian Neural Network Posteriors Really Like?
Pavel Izmailov (New York University) · Sharad Vikram (Google) · Matthew Hoffman (Google) · Andrew Wilson (New York University)

On the difficulty of unbiased alpha divergence minimization
Tomas Geffner (UMass Amherst) · Justin Domke (University of Massachusetts, Amherst)

On Robust Mean Estimation under Coordinate-level Corruption
Zifan Liu (University of Wisconsin-Madison) · Jong Ho Park (UW-Madison) · Theo Rekatsinas (University of Wisconsin-Madison) · Christos Tzamos (UW-Madison)

Reward Identification in Inverse Reinforcement Learning
Kuno Kim (Stanford University) · Shivam Garg (Stanford University) · Kirankumar Shiragur (Stanford University) · Stefano Ermon (Stanford University)

Joining datasets via data augmentation in the label space for neural networks
Mingfeng Ou (Tongji University) · Junbo Zhao (New York University) · linji Xue (Graviti inc.) · Yunkai Cui (Graviti) · Gang Chen (Zhejiang University) · Sai Wu (Zhejiang Univ)

Opening the Blackbox: Accelerating Neural Differential Equations by Regularizing Internal Solver Heuristics
Avik Pal (Indian Institute of Technology Kanpur) · Yingbo Ma (Julia Computing) · Viral Shah (Julia Computing) · Christopher Rackauckas (Massachusetts Institute of Technology)

Pure Exploration and Regret Minimization in Matching Bandits
Flore Sentenac (CREST) · Jialin Yi (London School of Economics) · Clément Calauzènes (Criteo AI Lab) · Vianney Perchet (ENSAE & Criteo AI Lab) · Milan Vojnovic (London School of Economics)

Model-Targeted Poisoning Attacks with Provable Convergence
Fnu Suya (University of Virginia) · Saeed Mahloujifar (Princeton University) · Anshuman Suri (University of Virginia) · David Evans (University of Virginia) · Yuan Tian (University of Virginia)

Crowdsourcing via Annotator Co-occurrence Imputation and Provable Symmetric Nonnegative Matrix Factorization
Shahana Ibrahim (Oregon State University) · Xiao Fu (Oregon State University)

Offline Reinforcement Learning with Pseudometric Learning
Robert Dadashi (Google Research) · Shideh Rezaeifar (University of Geneva) · Nino Vieillard (Google Brain) · Léonard Hussenot (Google Research, Brain Team) · Olivier Pietquin (GOOGLE BRAIN) · Matthieu Geist (Google)

Making transport more robust and interpretable by moving data through a small number of anchor points
Chi-Heng Lin (Georgia Institute of Technology) · Mehdi Azabou (Georgia Institute of Technology) · Eva Dyer (Georgia Tech)

Robust Representation Learning via Perceptual Similarity Metrics
Saeid A Taghanaki (Autodesk) · Kristy Choi (Stanford University) · Amir Hosein Khasahmadi (Autodesk AI Lab) · Anirudh Goyal (Université de Montréal)

Incentivizing Compliance with Algorithmic Instruments
Dung Ngo (University of Minnesota) · Logan Stapleton (University of Minnesota) · Vasilis Syrgkanis (Microsoft Research) · Steven Wu (Carnegie Mellon University)

Conjugate Energy-Based Models
Hao Wu (Northeastern University) · Babak Esmaeili (Northeastern University) · Michael Wick (Oracle Labs) · Jean-Baptiste Tristan (Boston College) · Jan-Willem van de Meent (Northeastern University)

On Signal-to-Noise Ratio Issues in Variational Inference for Deep Gaussian Processes
Tim G. J. Rudner (University of Oxford) · Oscar Key (UCL) · Yarin Gal (University of Oxford) · Tom Rainforth (University of Oxford)

Representation Matters: Offline Pretraining for Sequential Decision Making
Mengjiao Yang (Google Brain) · Ofir Nachum (Google Brain)

Variational Empowerment as Representation Learning for Goal-Conditioned Reinforcement Learning
Jongwook Choi (University of Michigan) · Archit Sharma () · Honglak Lee (Google / U. Michigan) · Sergey Levine (Google) · Shixiang Gu (Google)

Differentially Private Correlation Clustering
Mark Bun (Boston University) · Marek Elias (CWI) · Janardhan Kulkarni (Microsoft Research)

Leveraging Language to Learn Program Search Heuristics and Abstractions
Catherine Wong (Massachusetts Institute of Technology) · Kevin Ellis (Cornell University) · Josh Tenenbaum (MIT) · Jacob Andreas (UC Berkeley)

Stability and Convergence of Stochastic Gradient Clipping: Beyond Lipschitz Continuity and Smoothness
Vien Van Mai (KTH Royal Institute of Technology) · Mikael Johansson (KTH Royal Institute of Technology)

Implicit representation of probability distributions on the rotation manifold
Kieran Murphy (Google Research) · Carlos Esteves (Google Research) · Varun Jampani (Google Research) · Srikumar Ramalingam (Google) · Ameesh Makadia (Google Research)

Boosting for Online Convex Optimization
Elad Hazan (Princeton University) · Karan Singh (Microsoft Research)

Exploration in Approximate Hyper-State Space for Meta Reinforcement Learning
Luisa Zintgraf (University of Oxford) · Leo Feng (Mila) · Cong Lu (University of Oxford) · Maximilian Igl (University of Oxford) · Kristian Hartikainen (UC Berkeley) · Katja Hofmann (Microsoft) · Shimon Whiteson (University of Oxford)

Dropout: Explicit Forms and Capacity Control
Raman Arora (Johns Hopkins University) · Peter Bartlett ("University of California, Berkeley") · Poorya Mianjy (Johns Hopkins University) · Nati Srebro (Toyota Technological Institute at Chicago)

Training Recurrent Neural Networks via Forward Propagation Through Time
Anil Kag (Boston University) · Venkatesh Saligrama (Boston University)

Provably Strict Generalisation Benefit for Equivariant Models
Bryn Elesedy (University of Oxford) · Sheheryar Zaidi (University of Oxford)

On the Implicit Bias of Initialization Shape: Beyond Infinitesimal Mirror Descent
Shahar Azulay (TAU) · Edward Moroshko (Technion) · Mor Shpigel Nacson (Technion) · Blake Woodworth (Toyota Technological Institute at Chicago) · Nati Srebro (Toyota Technological Institute at Chicago) · Amir Globerson (Tel Aviv University, Google) · Daniel Soudry (Technion)

HEMET: A Homomorphic-Encryption-Friendly Privacy-Preserving Mobile Neural Network Architecture
Qian Lou (Indiana University) · Lei Jiang (Indiana University)

On-Off Center-Surround Receptive Fields for Accurate and Robust Image Classification
Zahra Babaiee (TU Wien) · Ramin Hasani (MIT) · Mathias Lechner (IST Austria) · Daniela Rus (MIT CSAIL) · Radu Grosu (TU Wien)

Equivariant Networks for Pixelized Spheres
Mehran Shakerinava (McGill - Mila) · Siamak Ravanbakhsh (McGill - Mila)

Agnostic Learning of Halfspaces with Gradient Descent via Soft Margins
Spencer Frei (UCLA) · Yuan Cao (UCLA) · Quanquan Gu (University of California, Los Angeles)

On the Explicit Role of Initialization on the Convergence and Implicit Bias of Overparametrized Linear Networks
Hancheng Min (Johns Hopkins University) · Salma Tarmoun (Johns Hopkins University) · Rene Vidal (Johns Hopkins University, USA) · Enrique Mallada (Johns Hopkins University)

Provable Generalization of SGD-trained Neural Networks of Any Width in the Presence of Adversarial Label Noise
Spencer Frei (UCLA) · Yuan Cao (UCLA) · Quanquan Gu (University of California, Los Angeles)

Problem Dependent View on Structured Thresholding Bandit Problems
James Cheshire (Otto von Guericke Universität Magdeburg) · Pierre MENARD (Inria) · Alexandra Carpentier (Otto-von-Guericke University)

Understanding self-supervised learning dynamics without contrastive pairs
Yuandong Tian (Facebook AI Research) · Xinlei Chen (FAIR) · Surya Ganguli (Stanford)

Evaluating Robustness of Predictive Uncertainty Estimation: Are Dirichlet-based Models Reliable?
Anna-Kathrin Kopetzki (Technical University of Munich) · Bertrand Charpentier (Technical University of Munich) · Daniel Zügner (Technical University of Munich) · Sandhya Giri (Technical University of Munich) · Stephan Günnemann (Technical University of Munich)

Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Training and Effective Adaptation
Haoxiang Wang (University of Illinois at Urbana-Champaign) · Han Zhao (University of Illinois at Urbana-Champaign) · Bo Li (UIUC)

Is Pessimism Provably Efficient for Offline RL?
Ying Jin (Stanford University) · Zhuoran Yang (Princeton University) · Zhaoran Wang (Northwestern U)

Directed Graph Embeddings in Pseudo-Riemannian Manifolds
Aaron Sim (BenevolentAI) · Maciej Wiatrak (BenevolentAI) · Angus Brayne (BenevolentAI) · Páidí Creed (BenevolentAI) · Saee Paliwal (Benevolent AI)

Learning and Planning in Complex Action Spaces
Thomas Hubert (DeepMind) · Julian Schrittwieser (DeepMind) · Ioannis Antonoglou (Deepmind) · Mohammadamin Barekatain (DeepMind) · Simon Schmitt (DeepMind) · David Silver (Google DeepMind)

A theory of high dimensional regression with arbitrary correlations between input features and target functions: sample complexity, multiple descent curves and a hierarchy of phase transitions
Gabriel Mel (Stanford University) · Surya Ganguli (Stanford)

Train simultaneously, generalize better: Stability of gradient-based minimax learners
Farzan Farnia (Massachusetts Institute of Technology) · Asuman Ozdaglar (MIT)

Fairness and Bias in Online Selection
Jose Correa (Universidad de Chile) · Andres Cristi (Universidad de Chile) · Paul Duetting (Google Research) · Ashkan Norouzi-Fard (Google)

Hierarchical Clustering of Data Streams: Scalable Algorithms and Approximation Guarantees
Danny Vainstein (Tel-Aviv University) · Anand Rajagopalan (Google) · Claudio Gentile (Google Research) · Cecilia Procopiuc (Google) · Gui Citovsky (Google) · Fabio Vitale (University of Lille & INRIA Lille)

WILDS: A Benchmark of in-the-Wild Distribution Shifts
Pang Wei Koh (Stanford University) · Shiori Sagawa (Stanford University) · Henrik Marklund (Stanford) · Sang Michael Xie (Stanford University) · Marvin Zhang (UC Berkeley) · Akshay Balsubramani (Stanford) · Weihua Hu (Stanford University) · Michihiro Yasunaga (Stanford University) · Richard Lanas Phillips (Cornell University) · Irena Gao (Stanford University) · Tony Lee (Stanford University) · Etienne David (INRAE) · Ian Stavness (University of Saskatchewan) · Wei Guo (The University of Tokyo) · Berton Earnshaw (Recursion) · Imran Haque (Recursion) · Sara Beery (Caltech) · Jure Leskovec (Stanford University) · Anshul Kundaje (Stanford University) · Emma Pierson (Microsoft) · Sergey Levine (UC Berkeley) · Chelsea Finn (Stanford) · Percy Liang (Stanford University)

PsiPhi-Learning: Reinforcement Learning with Demonstrations using Successor Features and Inverse Temporal Difference Learning
Angelos Filos (University of Oxford) · Clare Lyle (University of Oxford) · Yarin Gal (University of Oxford) · Sergey Levine (UC Berkeley) · Natasha Jaques (Google Brain, UC Berkeley) · Gregory Farquhar (University of Oxford)

Dash: Semi-Supervised Learning with Dynamic Thresholding
Yi Xu (Alibaba Group (U.S.) Inc.) · Lei Shang (Alibaba Group) · Jinxing Ye (Alibaba) · Qi Qian (Alibaba Group) · Yufeng Li (Nanjing University) · Baigui Sun (Alibaba Group) · Hao Li (Alibaba Group) · rong jin (alibaba group)

Private Alternating Least Squares: (Nearly) Optimal Privacy/Utility Trade-off for Matrix Completion
Steve Chien (Google) · Prateek Jain (Google Research) · Walid Krichene (Google Research) · Steffen Rendle (Google) · Shuang Song (Google) · Abhradeep Thakurta (Google) · Li Zhang (Google)

ADOM: Accelerated Decentralized Optimization Method for Time-Varying Networks
Dmitry Kovalev (KAUST) · Egor Shulgin (KAUST and MIPT) · Peter Richtarik (KAUST) · Alexander Rogozin (Moscow Institute of Physics and Technology) · Alexander Gasnikov (Moscow Institute of Physics and Technology)

Trees with Attention for Set Prediction Tasks
Roy Hirsch (Tel-Aviv University) · Ran Gilad-Bachrach (Tel-Aviv University)

Safe Reinforcement Learning Using Advantage-Based Intervention
Nolan Wagener (Georgia Tech) · Ching-An Cheng (Microsoft Research) · Byron Boots (University of Washington)

Elementary superexpressive activations
Dmitry Yarotsky (Skolkovo Institute of Science and Technology)

Characterizing Structural Regularities of Labeled Data in Overparameterized Models
Ziheng Jiang (University of Washington) · Chiyuan Zhang (Google Research) · Kunal Talwar (Apple) · Michael Mozer (Google Research & U. Colorado Boulder)

Finding Relevant Information via a Discrete Fourier Expansion
Mohsen Heidari (Purdue University) · Jithin Sreedharan (Wadhwani Institute for Artificial Intelligence) · Gil Shamir (Google) · Wojciech Szpankowski (Purdue University)

ChaCha for Online AutoML
Qingyun Wu (Microsoft Research) · Chi Wang (Microsoft Research) · John Langford (Microsoft Research) · Paul Mineiro (Microsoft) · Marco Rossi (Microsoft Corporation)

Valid Causal Inference with (Some) Invalid Instruments
Jason Hartford (University of British Columbia) · Victor Veitch (Google; University of Chicago) · Dhanya Sridhar (Columbia University) · Kevin Leyton-Brown (University of British Columbia)

Decoupling Representation Learning from Reinforcement Learning
Adam Stooke (UC Berkeley) · Kimin Lee (UC Berkeley) · Pieter Abbeel (UC Berkeley & Covariant) · Michael Laskin (UC Berkeley)

Quantifying Ignorance in Individual-Level Causal-Effect Estimates under Hidden Confounding
Andrew Jesson (University of Oxford) · Sören Mindermann (University of Oxford) · Yarin Gal (University of Oxford) · Uri Shalit (Technion)

Interpretable Stability Bounds for Spectral Graph Filters
Henry Kenlay (University of Oxford) · Dorina Thanou (EPFL) · Xiaowen Dong (University of Oxford)

Goal-Conditioned Reinforcement Learning with Imagined Subgoals
Elliot Chane-Sane (INRIA Paris) · Cordelia Schmid (Inria/Google) · Ivan Laptev (INRIA Paris)

A Modular Analysis of Provable Acceleration via Polyak's Momentum: Training a Wide ReLU Network and a Deep Linear Network
Jun-Kun Wang (Georgia Institute of Technology) · Chi-Heng Lin (Georgia Institute of Technology) · Jacob Abernethy (Georgia Institute of Technology)

A General Framework For Detecting Anomalous Inputs to DNN Classifiers
Jayaram Raghuram (University of Wisconsin, Madison) · Varun Chandrasekaran (University of Wisconsin) · Somesh Jha (University of Wisconsin, Madison) · Suman Banerjee (University of Wisconsin, Madison)

A Policy Gradient Algorithm for Learning to Learn in Multiagent Reinforcement Learning
Dong Ki Kim (MIT) · Miao Liu (IBM) · Matthew Riemer (IBM Research) · Chuangchuang Sun (MIT) · Marwa Abdulhai (MIT) · Golnaz Habibi (MIT) · Sebastian Lopez-Cot (MIT) · Gerald Tesauro (IBM Research) · Jonathan How (MIT)

ACE: Explaining cluster from an adversarial perspective
Yang Lu (University of Washington) · Timothy C Yu (University of Washington) · Giancarlo Bonora (University of Washington) · William Stafford Noble (University of Washington)

Massively Parallel and Asynchronous Tsetlin Machine Architecture Supporting Almost Constant-Time Scaling
Ole-Christoffer Granmo (University of Agder) · Rohan Kumar Yadav (University of Agder) · Kuruge Darshana Abeyrathna (University of Agder, Norway) · Lei Jiao (University of Agder) · Rupsa Saha (University of Agder) · Bimal Bhattarai (University of Agder) · Saeed Rahimi Gorji (University of Agder) · Morten Goodwin (University of Agder)

Projection techniques to update the truncated SVD of evolving matrices with applications
Vasileios Kalantzis (IBM Research) · Georgios Kollias (IBM) · Shashanka Ubaru (IBM Research) · Athanasios N. Nikolakopoulos (Amazon) · Lior Horesh (IBM Research) · Kenneth Clarkson (IBM Research)

RRL: Resnet as representation for Reinforcement Learning
Rutav Shah (Indian Institute of Technology, Kharagpur) · Vikash Kumar (Univ. Of Washington)

Aggregating From Multiple Target-Shifted Sources
Changjian Shui (Université Laval) · Zijian Li (Guangdong University of Technology) · Jiaqi Li (University of Western Ontario) · Christian Gagne (Université Laval) · Charles X. Ling (Western University) · Boyu Wang (University of Western Ontario)

Model-Based Reinforcement Learning via Latent-Space Collocation
Oleh Rybkin (University of Pennsylvania) · Chuning Zhu (University of Pennsylvania) · Anusha Nagabandi (UC Berkeley) · Kostas Daniilidis (University of Pennsylvania) · Igor Mordatch (Google Brain) · Sergey Levine (UC Berkeley)

Learning Interaction Kernels for Agent Systems on Riemannian Manifolds
Mauro Maggioni (Johns Hopkins University) · Jason Miller (Johns Hopkins University) · Hongda Qiu (Johns Hopkins University) · Ming Zhong (Johns Hopkins University)

Adapting to misspecification in contextual bandits with offline regression oracles
Sanath Kumar Krishnamurthy (Stanford University) · Vitor Hadad () · Susan Athey (Stanford University)

Asynchronous Distributed Learning : Adapting to Gradient Delays without Prior Knowledge
Rotem Zamir Aviv (Technion) · Kfir Levy (Technion) · Ido Hakimi (Technion - Israel Institute of Technology) · Assaf Schuster (Technion)

Accurate Post Training Quantization With Small Calibration Sets
Itay Hubara (Habana Labs) · Yury Nahshan (Intel Corp) · Yair Hanani (Habana Labs) · Ron Banner (Habana Labs) · Daniel Soudry (Technion)

Unbiased Gradient Estimation in Unrolled Computation Graphs with Persistent Evolution Strategies
Paul Vicol (University of Toronto) · Luke Metz (Google Brain) · Jascha Sohl-Dickstein (Google Brain)

12-Lead ECG Reconstruction via Koopman Operators
Tomer Golany (Technion - Israel Institute of Technology) · Kira Radinsky (Technion- Israel institute of technology) · Daniel Freedman (Google Israel) · Saar Minha (Assaf Harofeh Medical Center)

Robust Policy Gradient against Strong Data Corruption
Xuezhou Zhang (UW-Madison) · Yiding Chen (University of Wisconsin-Madison) · Jerry Zhu (University of Wisconsin-Madison) · Wen Sun (Cornell University)

Backdoor Scanning for Deep Neural Networks through K-Arm Optimization
Guangyu Shen (Purdue University) · Yingqi Liu (Purdue University) · Guanhong Tao (Purdue University) · Shengwei An (Purdue University) · Qiuling Xu (Purdue University) · Siyuan Cheng (Purdue University) · Shiqing Ma (Rutgers University) · Xiangyu Zhang (Purdue University)

Robust Learning for Data Poisoning Attacks
Yunjuan Wang (Johns Hopkins University) · Poorya Mianjy (Johns Hopkins University) · Raman Arora (Johns Hopkins University)

Calibrate Before Use: Improving Few-shot Performance of Language Models
Zihao Zhao (UC Berkeley) · Eric Wallace (U.C. Berkeley) · Shi Feng (University of Maryland) · Dan Klein (UC Berkeley) · Sameer Singh (University of California, Irvine)

OptiDICE: Offline Policy Optimization via Stationary Distribution Correction Estimation
Jongmin Lee (KAIST) · Wonseok Jeon (MILA, McGill University) · Byung-Jun Lee (Gauss Labs Inc.) · Joelle Pineau (McGill University / Facebook) · Kee-Eung Kim (KAIST)

A Discriminative Technique for Multiple-Source Adaptation
Corinna Cortes (Google Research) · Mehryar Mohri (Google Research and Courant Institute of Mathematical Sciences) · Ananda Theertha Suresh (Google Research) · Ningshan Zhang (Hudson River Trading)

Distributed Second Order Methods with Fast Rates and Compressed Communication
Rustem Islamov (MIPT) · Xun Qian (KAUST) · Peter Richtarik (KAUST)

Relative Deviation Margin Bounds
Corinna Cortes (Google Research) · Mehryar Mohri (Google Research and Courant Institute of Mathematical Sciences) · Ananda Theertha Suresh (Google Research)

An exact solver for the Weston-Watkins SVM subproblem
Yutong Wang (University of Michigan) · Clay Scott (University of Michigan)

Weisfeiler and Lehman Go Topological: Message Passing Simplicial Networks
Cristian Bodnar (University of Cambridge) · Fabrizio Frasca (Twitter, Imperial College London) · Yuguang Wang (Max Planck Institute for Mathematics in the Sciences; Shanghai Jiao Tong University; University of New South Wales) · Nina Otter (UCLA) · Guido Montufar (UCLA) · Pietro Lió (University of Cambridge) · Michael Bronstein (Imperial College / Twitter)

Do We Actually Need Dense Over-Parameterization? In-Time Over-Parameterization in Sparse Training
Shiwei Liu (Eindhoven University of Technology) · Lu Yin (Eindhoven University of Technology) · Decebal Constantin Mocanu (University of Twente) · Mykola Pechenizkiy (TU Eindhoven)

BORE: Bayesian Optimization by Density-Ratio Estimation
Chi-Chun Tiao (University of Sydney) · Aaron Klein (AWS Berlin) · Matthias W Seeger (Amazon) · Edwin Bonilla (CSIRO's Data61) · Cedric Archambeau (Amazon Web Services) · Fabio Ramos (NVIDIA, University of Sydney)

RATT: Leveraging Unlabeled Data to Guarantee Generalization
Saurabh Garg (Carnegie Mellon University) · Sivaraman Balakrishnan (CMU) · Zico Kolter (Carnegie Mellon University / Bosch Center for AI) · Zachary Lipton (Carnegie Mellon University)

Distribution-Free Calibration Guarantees for Uniform-Mass Binning without Sample Splitting
Chirag Gupta (Carnegie Mellon University) · Aaditya Ramdas (Carnegie Mellon University)

Quantum algorithms for reinforcement learning with a generative model
Ashish Kapoor (Microsoft Research) · Robin Kothari (Microsoft) · Martin Roetteler (Microsoft) · Aarthi Sundaram (Microsoft) · Daochen Wang (University of Maryland)

Efficient Training of Robust Decision Trees Against Adversarial Examples
Daniël Vos (Delft University of Technology) · Sicco Verwer (TU Deflt)

AGENT: A Benchmark for Core Psychological Reasoning
Tianmin Shu (MIT) · Abhishek Bhandwaldar (MIT-IBM Watson AI Lab) · Chuang Gan (MIT-IBM Watson AI Lab) · Kevin Smith (MIT) · Shari Liu (MIT) · Dan Gutfreund (IBM) · Elizabeth Spelke (Harvard University) · Josh Tenenbaum (MIT) · Tomer Ullman (Harvard)

Correlation Clustering in Constant Many Parallel Rounds
Vincent Cohen-Addad (Google) · Silvio Lattanzi (Google) · Slobodan Mitrović (MIT) · Ashkan Norouzi-Fard (Google) · Nikos Parotsidis (Google) · Jakub Tarnawski (Microsoft Research)

How the Loss functionon affect the Genrelisation Perofrmance of Deep Learning based Age Estimation?
Ali Akbari (University of Surrey) · Muhammad Awais (University of Surrey) · Manijeh Bashar (University of Surrey) · Josef Kittler (University of Surrey)

Versatile Verification of Tree Ensembles
Laurens Devos (KU Leuven) · Wannes Meert (KU Leuven) · Jesse Davis (KU Leuven)

Asymptotics of Ridge Regression in Convolutional Models
Mojtaba Sahraee-Ardakan (UCLA) · Tung Mai (Adobe Research) · Anup Rao (Adobe Research) · Ryan A. Rossi (Adobe Research) · Sundeep Rangan (NYU) · Alyson Fletcher (UCLA)

Efficient Performance Bounds for Primal-Dual Reinforcement Learning from Demonstrations
Angeliki Kamoutsi (ETH Zurich) · Goran Banjac (ETH Zurich) · John Lygeros (ETH Zürich)

From Poincar\'e Recurrence to Convergence in Imperfect Information Games: Finding Equilibrium via Regularization
Julien Perolat (DeepMind) · Remi Munos (DeepMind) · Jean-Baptiste Lespiau (DeepMind) · Shayegan Omidshafiei (DeepMind) · Mark Rowland (DeepMind) · Pedro Ortega (DeepMind) · Neil Burch (DeepMind) · Thomas Anthony (DeepMind) · David Balduzzi (XTX Markets) · Bart De Vylder (DeepMind) · Georgios Piliouras (Singapore University of Technology and Design) · Marc Lanctot (DeepMind) · Karl Tuyls (DeepMind)

MSA Transformer
Roshan Rao (UC Berkeley) · Jason Liu (Facebook AI Reseach) · Robert Verkuil (Facebook AI Research) · Joshua Meier (Facebook AI Research) · John Canny (UC Berkeley) · Pieter Abbeel (UC Berkeley & Covariant) · Tom Sercu (Facebook AI Research) · Alexander Rives (NYU)

Dynamic Balancing for Model Selection in Bandits and RL
Ashok Cutkosky (Boston University) · Christoph Dann (Google) · Abhimanyu Das (Google) · Claudio Gentile (Google Research) · Aldo Pacchiano (UC Berkeley) · Manish Purohit (Google Research)

Controlling Graph Dynamics with Reinforcement Learning and Graph Neural Networks
Eli Meirom (NVIDIA Research) · Haggai Maron (NVIDIA Research) · Shie Mannor (Technion) · Gal Chechik (NVIDIA / Bar-Ilan University)

Regularizing towards Causal Invariance: Linear Models with Proxies
Michael Oberst (MIT) · Nikolaj Thams (University of Copenhagen) · Jonas Peters (University of Copenhagen) · David Sontag (Massachusetts Institute of Technology)

Stochastic Iterative Graph Matching
Linfeng Liu (Tufts University) · Michael C. Hughes (Tufts University) · Soha Hassoun () · Liping Liu (Tufts University)

Operationalizing Complex Causes: A Pragmatic View of Mediation
Limor Gultchin (University of Oxford) · David Watson (University College London) · Matt J. Kusner (University College London) · Ricardo Silva (University College London)

PHEW: Constructing Sparse Networks that Learn Fast and Generalize Well without Training Data
Shreyas Malakarjun Patil (Georgia Institute of Technology) · Constantine Dovrolis (Georgia Tech)

Streaming and Distributed Algorithms for Robust Column Subset Selection
Shuli Jiang (Carnegie Mellon University) · Dongyu Li (Carnegie Mellon University) · Irene Mengze Li (Carnegie Mellon University) · Arvind Mahankali (Carnegie Mellon University) · David Woodruff (Carnegie Mellon University)

Shape Transformation with Deep Implicit Functions by Matching Implicit Features
Yunlu Chen (University of Amsterdam) · Basura Fernando (Agency for Science, Technology and Research (A*STAR)) · Hakan Bilen (University of Edinburgh) · Thomas Mensink (Google Research / University of Amsterdam) · Efstratios Gavves (University of Amsterdam )

Emphatic Algorithms for Deep Reinforcement Learning
Ray Jiang (DeepMind) · Tom Zahavy (DeepMind) · Zhongwen Xu (DeepMind) · Adam White (Deepmind, University of Alberta) · Matteo Hessel (DeepMind) · Charles Blundell (DeepMind) · Hado van Hasselt (DeepMind)

Proximal Causal Learning with Kernels: Two-Stage Estimation and Moment Restriction
Afsaneh Mastouri (University College London) · Yuchen Zhu (University College London) · Limor Gultchin (University of Oxford) · Anna Korba (CREST/ENSAE) · Ricardo Silva (University College London) · Matt J. Kusner (University College London) · Arthur Gretton (Gatsby Computational Neuroscience Unit) · Krikamol Muandet (Max Planck Institute for Intelligent Systems)

Solving high-dimensional parabolic PDEs using the tensor train format
Lorenz Richter (Freie Universität Berlin, BTU Cottbus-Senftenberg, dida) · Leon Sallandt (Technische Universitaet Berlin) · Nikolas Nüsken (Universität Potsdam)

DriftSurf: Stable-State / Reactive-State Learning under Concept Drift
Ashraf Tahmasbi (Iowa State University) · Ellango Jothimurugesan (CMU) · Srikanta Tirthapura (Iowa State University) · Phillip Gibbons (CMU)

A Unified Bayesian Framework for Discriminative and Generative Continual Learning
Abhishek Kumar (Microsoft) · Sunabha Chatterjee (SAP Labs India) · Piyush Rai (IIT Kanpur)

Learning from Noisy Labels with No Change to the Training Process
Mingyuan Zhang (University of Pennsylvania) · Jane Lee (University of Pennsylvania) · Shivani Agarwal (University of Pennsylvania)

Equivariant Learning of Stochastic Fields: Gaussian Processes and Steerable Conditional Neural Processes
Peter Holderrieth (University of Oxford) · Michael Hutchinson (University of Oxford) · Yee Whye Teh (Oxford and DeepMind)

On the Predictability of Pruning Across Scales
Jonathan Rosenfeld (MIT) · Jonathan Frankle (MIT CSAIL) · Michael Carbin (MIT) · Nir Shavit (MIT)

Bayesian Deep Learning via Subnetwork Inference
Erik Daxberger (University of Cambridge & MPI for Intelligent Systems, Tübingen) · Eric Nalisnick (University of Amsterdam) · James U Allingham (University of Cambridge) · Javier Antorán (University of Cambridge) · Jose Miguel Hernandez-Lobato (University of Cambridge)

Learning node representations using stationary flow prediction on large payment and cash transaction networks
Ciwan Ceylan (KTH Royal Institute of Technology & SEB) · Salla Franzén (SEB AB) · Florian T. Pokorny (KTH Royal Institute of Technology)

Reasoning Over Virtual Knowledge Bases With Open Predicate Relations
Haitian Sun () · Patrick Verga (UMass, Amherst) · Bhuwan Dhingra (CMU) · Ruslan Salakhutdinov (Carnegie Mellen University) · William Cohen (Google AI)

Inference for Network Regression Models with Community Structure
Mengjie Pan (Facebook) · Tyler Mccormick (University of Washington) · Bailey Fosdick (Colorado State University)

Scalable Evaluation of Multi-Agent Reinforcement Learning with Melting Pot
Joel Z Leibo (DeepMind) · Edgar Duenez-Guzman (DeepMind) · Alexander Vezhnevets (DeepMind) · John Agapiou (DeepMind) · Peter Sunehag () · Raphael Koster (DeepMind) · Jayd Matyas (DeepMind) · Charles Beattie (DeepMind Technologies Limited) · Igor Mordatch (Google Brain) · Thore Graepel (DeepMind)

Auto-NBA: Efficient and Effective Search Over The Joint Space of Networks, Bitwidths, and Accelerators
Yonggan Fu (Rice University) · Yongan Zhang (Rice University) · Yang Zhang (MIT-IBM Watson AI Lab) · David Cox (MIT-IBM Watson AI Lab) · Yingyan Lin (Rice University)

Measuring Robustness in Deep Learning Based Compressive Sensing
Mohammad Zalbagi Darestani (Rice University) · Akshay Chaudhari (Stanford University) · Reinhard Heckel (Rice University)

Sparse Bayesian Learning via Stepwise Regression
Sebastian Ament (Cornell University) · Carla Gomes (Cornell University)

Explanations for Monotonic Classifiers.
Joao Marques-Silva (IRIT, CNRS) · Thomas Gerspacher (ANITI) · Martin Cooper (University of Toulouse 3) · Alexey Ignatiev (Monash University) · Nina Narodytska (VMWare)

High-Performance Large-Scale Image Recognition Without Normalization
Andy Brock (DeepMind) · Soham De (DeepMind) · Samuel Smith (DeepMind) · Karen Simonyan (DeepMind)

Double-Win Quant: Aggressively Winning Robustness of Quantized Deep Neural Networks via Random Precision Training and Inference
Yonggan Fu (Rice University) · Qixuan Yu (Rice University) · Meng Li (Facebook Inc) · Vikas Chandra (Facebook) · Yingyan Lin (Rice University)

Unifying Vision-and-Language Tasks via Text Generation
Jaemin Cho (Seoul National University) · Jie Lei (UNC Chapel Hill) · Hao Tan (University of North Carolina Chapel Hill) · Mohit Bansal (University of North Carolina at Chapel Hill)

On a Combination of Alternating Minimization and Nesterov's Momentum
Sergey Guminov (Higher School of Economics) · Pavel Dvurechenskii (Weierstrass Institute) · Nazarii Tupitsa (Institute for Information Transmission Problems) · Alexander Gasnikov (Moscow Institute of Physics and Technology)

Grounding Language to Entities and Dynamics for Generalization in Reinforcement Learning
Austin Hanjie (Princeton University) · Victor Zhong (University of Washington) · Karthik Narasimhan (Princeton)

Lossless Compression of Efficient Private Local Randomizers
Vitaly Feldman (Google Brain) · Kunal Talwar (Apple)

Generative Video Transformer: Can Objects be the Words?
Yi-Fu Wu (Rutgers University) · Jaesik Yoon (SAP) · Sungjin Ahn (Rutgers University)

Differentially Private Bayesian Inference for Generalized Linear Models
Tejas Kulkarni (Aalto University) · Joonas Jälkö (Aalto University) · Antti Koskela (University of Helsinki) · Samuel Kaski (Aalto University and University of Manchester) · Antti Honkela (University of Helsinki)

Heterogeneity for the Win: One-Shot Federated Clustering
Don Kurian Dennis (Carnegie Mellon University) · Tian Li (Carnegie Mellon University) · Virginia Smith (Carnegie Mellon University)

Randomized Dimensionality Reduction for Clustering
Shyam Narayanan (Massachusetts Institute of Technology) · Sandeep Silwal (MIT) · Piotr Indyk (MIT) · Or Zamir (Tel Aviv University)

Principal Bit Analysis: Autoencoding with Schur-Concave Loss
Sourbh Bhadane (Cornell University) · Aaron Wagner (Cornell University) · Jayadev Acharya (Cornell University)

Improved Algorithms for Agnostic Pool-based Active Classification
Julian Katz-Samuels (University of Wisconsin-Madison) · Jifan Zhang (University of Wisconsin) · Lalit Jain (University of Washington) · Kevin Jamieson (University of Washington)

Additive Error Guarantees for Weighted Low Rank Approximation
Aditya Bhaskara (University of Utah) · Aravinda Kanchana Ruwanpathirana (University of Utah) · Pruthuvi Maheshakya Wijewardena (University of Utah)

A New Formalism, Method and Open Issues for Zero-Shot Coordination
Johannes Treutlein (University of Toronto, Vector Institute) · Michael Dennis (UC Berkeley) · Caspar Oesterheld (Duke) · Jakob Foerster (Facebook AI Research)

Discovering symbolic policies with deep reinforcement learning
Sookyung Kim (Lawrence Livermore National Laboratory) · Mikel Landajuela Larma (Lawrence Livermore National Laboroatory) · Brenden Petersen (Lawrence Livermore National Laboratory) · Claudio Santiago (LLNL) · Ruben Glatt (Lawrence Livermore National Laboratory (LLNL)) · Nathan Mundhenk (Lawrence Livermore National Labs) · Jacob Pettit (Lawrence Livermore National Laboratory) · Daniel Faissol (Lawrence Livermore National Laboratory)

Learning from History for Byzantine Robust Optimization
Sai Praneeth Reddy Karimireddy (EPFL) · Lie He (EPFL) · Martin Jaggi (EPFL)

Private Stochastic Convex Optimization: Optimal Rates in L1 Geometry
Hilal Asi (Stanford University) · Vitaly Feldman (Google Brain) · Tomer Koren (Tel Aviv University and Google) · Kunal Talwar (Apple)

Towards the Unification and Robustness of Perturbation and Gradient Based Explanations
Sushant Agarwal (University of Waterloo) · Shahin Jabbari (Harvard University) · Chirag Agarwal (Harvard University) · Sohini Upadhyay (Harvard University) · Steven Wu (Carnegie Mellon University) · Himabindu Lakkaraju (Harvard)

Multidimensional Scaling: Approximation and Complexity
Erik Demaine (MIT) · Adam C Hesterberg (Harvard John A. Paulson School Of Engineering And Applied Sciences) · Frederic Koehler (MIT) · Jayson Lynch (University of Waterloo) · John C Urschel (Massachusetts Institute of Technology)

Thinking Like Transformers
Gail Weiss (Technion) · Yoav Goldberg (Bar Ilan University) · Eran Yahav (Technion)

A Language for Counterfactual Generative Models
Zenna Tavares (MIT) · James Koppel (MIT) · Xin Zhang (Peking University) · Ria Das (MIT) · Armando Solar-Lezama (MIT)

A Deep Reinforcement Learning Approach to Marginalized Importance Sampling with the Successor Representation
Scott Fujimoto (McGill University) · David Meger (McGill University) · Doina Precup (McGill University / DeepMind)

End-to-End Learning of Coherent Probabilistic Forecasts for Hierarchical Time Series
Syama Sundar Yadav Rangapuram (Amazon) · Lucien D Werner (California Institute of Technology) · Konstantinos Benidis (Amazon Research) · Pedro Mercado (Amazon Research) · Jan Gasthaus (Amazon Research) · Tim Januschowski (Amazon Research)

Multi-Agent Training beyond Zero-Sum with Correlated Equilibrium Meta-Solvers
Luke Marris (DeepMind) · Paul Muller (DeepMind) · Marc Lanctot (DeepMind) · Karl Tuyls (DeepMind) · Thore Graepel (DeepMind)

Generalization Guarantees for Neural Architecture Search with Train-Validation Split
Samet Oymak (University of California, Riverside) · Mingchen Li (University of California, Riverside) · Mahdi Soltanolkotabi (University of Southern California)

Improving Breadth-Wise Backpropagation in Graph Neural Networks helps Learning Long-Range Dependencies.
Denis Lukovnikov (Ruhr University Bochum) · Asja Fischer (Ruhr University Bochum)

Three Operator Splitting with a Nonconvex Loss Function
Alp Yurtsever (MIT) · Varun Mangalick (MIT) · Suvrit Sra (MIT)

Practical and Private (Deep) Learning without Sampling or Shuffling
Peter Kairouz (Google) · Brendan McMahan (Google) · Shuang Song (Google) · Om Dipakbhai Thakkar (Google) · Abhradeep Thakurta (Google) · Zheng Xu (Google Research)

What does LIME really see in images?
Damien Garreau (Université Côte d'Azur) · Dina Mardaoui (Polytech Nice Sophia)

DANCE: Enhancing saliency maps using decoys
Yang Lu (University of Washington) · Wenbo Guo (Pennsylvania State University) · Xinyu Xing (The Pennsylvania State University) · William Stafford Noble (University of Washington)

EL-Attention: Memory Efficient Lossless Attention for Generation
Yu Yan (Microsoft) · Jiusheng Chen (Microsoft) · Weizhen Qi (University of Science and Technology of China) · Nikhil Bhendawade (Microsoft) · Yeyun Gong (Microsoft Research Asia) · Nan Duan (Microsoft Research) · Ruofei Zhang (Microsoft)

PC-MLP: Model-based Reinforcement Learning with Policy Cover Guided Exploration
Yuda Song (Carnegie Mellon University) · Wen Sun (Cornell University)

Globally-Robust Neural Networks
Klas Leino (Carnegie Mellon University) · Zifan Wang (Carnegie Mellon University) · Matt Fredrikson (Carnegie Mellon University)

DeepReDuce: ReLU Reduction for Fast Private Inference
Nandan Kumar Jha (New York University) · Zahra Ghodsi (New York University) · Siddharth Garg (New York University) · Brandon Reagen (New York University)

Characterizing the Gap Between Actor-Critic and Policy Gradient
Junfeng Wen (University of Alberta) · Saurabh Kumar (Stanford) · Ramki Gummadi (Google Brain) · Dale Schuurmans (University of Alberta)

Neural Symbolic Regression that scales
Luca Biggio (ETH Zürich) · Tommaso Bendinelli (CSEM) · Alexander Neitz (Max Planck Institute for Intelligent Systems) · Aurelien Lucchi (ETH Zurich) · Giambattista Parascandolo (ETH Zurich)

DeepWalking Backwards: From Embeddings Back to Graphs
Sudhanshu Chanpuriya (University of Massachusetts Amherst) · Cameron Musco (University of Massachusetts Amherst) · Konstantinos Sotiropoulos (Boston University) · Charalampos Tsourakakis (ISI Foundation, Boston University)

Deep Learning for Functional Data Analysis with Adaptive Basis Layers
Junwen Yao (UC Davis) · Jonas Mueller (Amazon Web Services) · Jane-Ling Wang (UC Davis)

Unsupervised Learning of Visual 3D Keypoints for Sensorimotor Control
Boyuan Chen (University of California, Berkeley) · Pieter Abbeel (UC Berkeley) · Deepak Pathak (CMU, FAIR)

Simple and Effective VAE Training with Calibrated Decoders
Oleh Rybkin (University of Pennsylvania) · Kostas Daniilidis (University of Pennsylvania) · Sergey Levine (UC Berkeley)

Coach-Player Multi-agent Reinforcement Learning for Dynamic Team Composition
Bo Liu (University of Texas, Austin) · Qiang Liu (UT Austin) · Peter Stone (University of Texas at Austin) · Animesh Garg (University of Toronto, Vector Institute, Nvidia) · Yuke Zhu (University of Texas - Austin) · Anima Anandkumar (California Institute of Technology)

A structured observation distribution for generative biological sequence prediction and forecasting
Eli N. Weinstein (Harvard) · Debora Marks (Harvard Medical School)

A Practical Method for Constructing Equivariant Multilayer Perceptrons for Arbitrary Matrix Groups
Marc Finzi (New York University) · Max Welling (University of Amsterdam) · Andrew Wilson (New York University)

Meta-Thompson Sampling
Branislav Kveton (Google Research) · Mikhail Konobeev (University of Alberta) · Manzil Zaheer (Google Research) · Chih-wei Hsu ( Google Research) · Martin Mladenov (Google) · Craig Boutilier (Google) · Csaba Szepesvari (DeepMind/University of Alberta)

An Integer Linear Programming Framework for Mining Constraints from Data
Tao Meng (University of California, Los Angeles) · Kai-Wei Chang (University of California, Los Angeles )

Tractable structured natural-gradient descent using local parameterizations
Wu Lin (University of British Columbia) · Frank Nielsen (Sony CSL, Japan) · Khan Emtiyaz (RIKEN) · Mark Schmidt (University of British Columbia)

A Tale of Two Efficient and Informative Negative Sampling Distributions
Shabnam Daghaghi (Rice University) · Tharun Medini (Rice University) · Beidi Chen (Rice University) · Mengnan Zhao (Rice University) · Nicholas Meisburger (Rice University) · Anshumali Shrivastava (Rice University)

Faster Kernel Matrix Algebra via Density Estimation
Arturs Backurs (TTIC) · Piotr Indyk (MIT) · Cameron Musco (UMass) · Tal Wagner (MIT)

Spectral Normalisation for Deep Reinforcement Learning: An Optimisation Perspective
Florin Gogianu (Bitdefender) · Tudor Berariu (Imperial College London) · Mihaela Rosca (DeepMind, UCL) · Claudia Clopath (Imperial College London) · Lucian Busoniu (Technical University of Cluj-Napoca) · Razvan Pascanu (DeepMind)

High-dimensional Experimental Design and Kernel Bandits
Romain Camilleri (University of Washington) · Kevin Jamieson (University of Washington) · Julian Katz-Samuels (University of Wisconsin-Madison)

Actionable Models: Unsupervised Offline Reinforcement Learning of Robotic Skills
Yevgen Chebotar (Google) · Karol Hausman (Google Brain) · Yao Lu (Google Research) · Ted Xiao (Google) · Dmitry Kalashnikov (Google Inc.) · Jacob Varley (Google) · Alexander Irpan (Google) · Benjamin Eysenbach (CMU, Google Brain) · Ryan Julian (Google) · Chelsea Finn (Google Brain) · Sergey Levine (Google)

Parallel and Flexible Sampling from Autoregressive Models via Langevin Dynamics
Vivek Jayaram (University of Washington) · John Thickstun (University of Washington)

Diffusion Earth Movers Distance and Distribution Embeddings
Alexander Tong (Yale University) · Amine Natik (MILA) · Guillaume Huguet (Mila) · Kincaid Macdonald (Yale University) · MANIK KUCHROO (Yale University) · Ronald Coifman (Yale University) · Guy Wolf (Université de Montréal; Mila) · Smita Krishnaswamy (Yale University)

SKIing on Simplices: Kernel Interpolation on the Permutohedral Lattice for Scalable Gaussian Processes
Sanyam Kapoor (New York University) · Marc Finzi (New York University) · Ke Alexander Wang (Stanford University) · Andrew Wilson (New York University)

Decomposed Mutual Information Estimation for Contrastive Representation Learning
Alessandro Sordoni (Microsoft Research) · Nouha Dziri (University of Alberta) · Hannes Schulz (Microsoft) · Geoff Gordon (Carnegie Mellon University) · Philip Bachman (Microsoft Research) · Remi Tachet des Combes (Microsoft Research Montreal)

When is Pessimism Warranted in Batch Policy Optimization?
Chenjun Xiao (Google / University of Alberta) · Yifan Wu (Carnegie Mellon University) · Jincheng Mei (University of Alberta / Google Brain) · Bo Dai (Google Brain) · Tor Lattimore (DeepMind) · Lihong Li (Google Research) · Csaba Szepesvari (DeepMind/University of Alberta) · Dale Schuurmans (Google / University of Alberta)

You Only Sample (Almost) Once: Linear Cost Self-Attention Via Bernoulli Sampling
Zhanpeng Zeng (University of Wisconsin-Madison) · Yunyang Xiong (University of Wisconsin-Madison) · Sathya Ravi (University of Illinois at Chicago) · Shailesh Acharya (American Family Insurance) · Glenn Fung (American Family Insurance) · Vikas Singh (University of Wisconsin Madison)

Beyond Variance Reduction: Understanding the True Impact of Baselines on Policy Optimization
Wesley Chung (Mila / McGill University) · Valentin Thomas (MILA) · Marlos C. Machado (DeepMind) · Nicolas Le Roux (Google)

Predict then Interpolate: A Simple Algorithm to Learn Stable Classifiers
Yujia Bao (MIT) · Shiyu Chang (MIT-IBM Watson AI Lab) · Regina Barzilay (MIT CSAIL)

Optimal Counterfactual Explanations in Tree Ensembles
Axel Parmentier (Ecole des Ponts) · Thibaut Vidal (Polytechnique Montreal & PUC-Rio)

Bayesian Optimistic Optimisation with Exponentially Decaying Regret
Hung Tran-The (Deakin University) · Sunil Gupta (Deakin University) · Santu Rana (Deakin University) · Svetha Venkatesh (Deakin University)

Few-shot Language Coordination by Modeling Theory of Mind
Hao Zhu (Carnegie Mellon University) · Graham Neubig (Carnegie Mellon University) · Yonatan Bisk (Carnegie Mellon University)

Cross-Gradient Aggregation for Decentralized Learning from Non-IID data
Yasaman Esfandiari (Iowa State University) · Sin Yong Tan (Iowa State University) · Zhanhong Jiang (Johnson Controls International) · Aditya Balu (Iowa State University) · Ethan Herron (Iowa State University) · Chinmay Hegde (New York University) · Soumik Sarkar (Iowa State University)

Learning Neural Network Subspaces
Mitchell Wortsman (University of Washington) · Maxwell Horton (Apple) · Carlos Guestrin (Apple & Univesity of Washington) · Ali Farhadi (University of Washington, Allen Institue for AI) · Mohammad Rastegari (University of Washington)

Recovering AES Keys with a Deep Cold Boot Attack
Itamar Zimerman (Tel Aviv University) · Eliya Nachmani (Tel-Aviv University & Facebook AI Research) · Lior Wolf (Facebook AI Research and Tel Aviv University)

Meta-Cal: Well-controlled Post-hoc Calibration by Ranking
Xingchen Ma (KU Leuven) · Matthew B Blaschko (KU Leuven)

ARMS: Antithetic-REINFORCE-Multi-Sample Gradient for Binary Variables
Alek Dimitriev (University of Texas at Austin) · Mingyuan Zhou (University of Texas at Austin)

Privacy-Preserving Feature Selection with Secure Multiparty Computation
Xiling Li (University of Washington) · Rafael Dowsley (Monash University) · Martine De Cock (University of Washington)

Adversarial Policy Learning in Two-party Competitive Games
Wenbo Guo (Pennsylvania State University) · Xian Wu (Penn State) · Sui Huang (Netflix) · Xinyu Xing (The Pennsylvania State University)

Towards Tight Bounds on the Sample Complexity of Average-reward MDPs
Yujia Jin (Stanford University) · Aaron Sidford (Stanford)

Posterior Value Functions: Hindsight Baselines for Policy Gradient Methods
Chris Nota (University of Massachusetts Amherst) · Philip Thomas (University of Massachusetts Amherst) · Bruno C. da Silva (University of Massachusetts)

Inverse Decision Modeling: Learning Interpretable Representations of Behavior
Daniel Jarrett (University of Cambridge) · Alihan Hüyük (University of Cambridge) · Mihaela van der Schaar (University of Cambridge and UCLA)

Memory Efficient Online Meta Learning
Durmus Alp Emre Acar (Boston University) · Ruizhao Zhu (Boston University) · Venkatesh Saligrama (Boston University)

Knowledge Enhanced Machine Learning Pipeline against Diverse Adversarial Attacks
Nezihe Merve Gürel (ETH Zurich) · Xiangyu Qi (Zhejiang University) · Luka Rimanic (ETH Zurich) · Ce Zhang (ETH Zurich) · Bo Li (UIUC)

Efficient Statistical Tests: A Neural Tangent Kernel Approach
Sheng Jia (University of Toronto) · Ehsan Nezhadarya (LG Electronics) · Yuhuai Wu (University of Toronto) · Jimmy Ba ()

Expressive 1-Lipschitz Neural Networks for Robust Multiple Graph Learning against Adversarial Attacks
Xin Zhao (Auburn University) · Zeru Zhang (Auburn University) · Zijie Zhang (Auburn University) · Lingfei Wu (IBM Research AI) · Jiayin Jin (Auburn University) · Yang Zhou (Auburn University) · Ruoming Jin (Kent State University) · Dejing Dou (" University of Oregon, USA") · Da Yan (University of Alabama at Birmingham)

Counterfactual Credit Assignment in Model-Free Reinforcement Learning
Thomas Mesnard (DeepMind) · Theophane Weber (DeepMind) · Fabio Viola (DeepMind) · Shantanu Thakoor (DeepMind) · Alaa Saade (DeepMind) · Anna Harutyunyan (DeepMind) · Will Dabney (DeepMind) · Thomas Stepleton (DeepMind) · Nicolas Heess (DeepMind) · Arthur Guez (Google DeepMind) · Eric Moulines (Ecole Polytechnique) · Marcus Hutter (DeepMind) · Lars Buesing (Deepmind) · Remi Munos (DeepMind)

SG-PALM: a Fast Physically Interpretable Tensor Graphical Model
Yu Wang (University of Michigan) · Alfred Hero (University of Michigan)

Robust Pure Exploration in Linear Bandits with Limited Budget
Ayya Alieva (Stanford University) · Ashok Cutkosky (Boston University) · Abhimanyu Das (Google)

Off-Belief Learning
Hengyuan Hu (Facebook AI Research) · Adam Lerer (Facebook AI Research) · Brandon Cui (Facebook AI Research) · Luis Pineda (Facebook AI Research) · Noam Brown (Facebook) · Jakob Foerster (Facebook AI Research)

Randomized Exploration in Reinforcement Learning with General Value Function Approximation
Haque Ishfaq (MILA / McGill University) · Qiwen Cui (Peking University) · Alex Ayoub (University of Alberta) · Viet Nguyen (McGill, Mila) · Zhuoran Yang (Princeton University) · Zhaoran Wang (Northwestern U) · Doina Precup (McGill University / DeepMind) · Lin Yang (UCLA)

The Distributed Discrete Gaussian Mechanism for Federated Learning with Secure Aggregation
Peter Kairouz (Google) · Ziyu Liu (Google) · Thomas Steinke (Google)

On-the-fly Rectification for Robust Large-Vocabulary Topic Inference
Moontae Lee (University of Illinois at Chicago) · Sungjun Cho (Georgia Institute of Technology) · Kun Dong (Cornell University) · David Mimno (Cornell University) · David Bindel (Cornell University)

Context-Aware Online Collective Inference for Templated Graphical Models
Charles Dickens (UCSC) · Connor Pryor (UCSC) · Eriq Augustine (University of California, Santa Cruz) · Alexander Miller (UCSC) · Lise Getoor (University of California Santa Cruz)

A Second look at Exponential and Cosine Step Sizes: Simplicity, Convergence, and Performance
Xiaoyu Li (Boston University) · Zhenxun Zhuang (Boston University) · Francesco Orabona (Boston University)

Parallelizing Legendre Memory Unit Training
Narsimha Reddy Chilkuri (University of Waterloo) · Chris Eliasmith (University of Waterloo)

Improved Denoising Diffusion Probabilistic Models
Alexander Nichol (Open AI) · Prafulla Dhariwal (OpenAI)

Image-Level or Object-Level? A Tale of Two Resampling Strategies for Long-Tailed Localization
Nadine Chang (Carnegie Mellon University) · Zhiding Yu (NVIDIA) · Yu-Xiong Wang (University of Illinois at Urbana-Champaign) · Anima Anandkumar (Caltech and NVIDIA) · Sanja Fidler (University of Toronto, NVIDIA) · Jose Alvarez (NVIDIA)

Optimal Estimation of High Dimensional Smooth Additive Function Based on Noisy Observations
Fan Zhou (Baidu Research) · Ping Li (Rugters University)

Scalable Variational Gaussian Processes via Harmonic Kernel Decomposition
Shengyang Sun (University of Toronto) · Jiaxin Shi (Microsoft Research) · Andrew Wilson (New York University) · Roger Grosse (University of Toronto and Vector Institute)

Structured World Belief for Reinforcement Learning in POMDP
Gautam Singh (Rutgers University) · Skand Peri (Rutgers University, New Jersey) · Junghyun Kim (Rutgers University) · Hyunseok Kim (Electronics and Telecommunications Research Institute (ETRI), Korea) · Sungjin Ahn (Rutgers University)

Prior Image-Constrained Reconstruction using Style-Based Generative Models
Varun A. Kelkar (University of Illinois at Urbana-Champaign) · Mark Anastasio (University of Illinois at Urbana-Champaign)

Vector Quantized Models for Planning
Sherjil Ozair (DeepMind) · Yazhe Li (Deepmind) · Ali Razavi (DeepMind) · Ioannis Antonoglou (Deepmind) · Aäron van den Oord (Google Deepmind) · Oriol Vinyals (Google DeepMind)

Segmenting Hybrid Trajectories using Latent ODEs
Ruian Shi (University of Toronto and Vector Institute) · Quaid Morris (Memorial Sloan Kettering Cancer Center, Vector Institute, and University of Toronto)

Value Alignment Verification
Daniel Brown (UC Berkeley) · Jordan Schneider (UT Austin) · Anca Dragan (University of California, Berkeley) · Scott Niekum (University of Texas at Austin)

Efficient Deviation Types and Learning for Hindsight Rationality in Extensive-Form Games
Dustin Morrill (University of Alberta; Alberta Machine Intelligence Institute) · Ryan D'Orazio (Université de Montréal) · Marc Lanctot (DeepMind) · James Wright (University of Alberta) · Michael Bowling (University of Alberta) · Amy Greenwald (Brown)

Learning Task Informed Abstractions
Xiang Fu (MIT) · Ge Yang (University of Chicago) · Pulkit Agrawal (MIT) · Tommi Jaakkola (MIT)

EMaQ: Expected-Max Q-Learning Operator for Simple Yet Effective Offline and Online RL
Seyed Kamyar Seyed Ghasemipour (University of Toronto) · Dale Schuurmans (Google / University of Alberta) · Shixiang Gu (Google)

CombOptNet: Fit the Right NP-Hard Problem by Learning Integer Programming Constraints
Anselm Paulus (Max Planck Institute For Intelligent Systems) · Michal Rolinek (Max Planck Institute for Intelligent Systems) · Vit Musil (Masaryk University) · Brandon Amos (Facebook AI Research) · Georg Martius (Max Planck Institute for Intelligent Systems)

Blind Pareto Fairness and Subgroup Robustness
Natalia Martinez (Duke University) · Martin Bertran (Duke University) · Afroditi Papadaki (University College London) · Miguel Rodrigues (University College London) · Guillermo Sapiro (Duke University)

Policy Gradient Bayesian Robust Optimization for Imitation Learning
Daniel Brown (UC Berkeley) · Ashwin Balakrishna (University of California, Berkeley) · Zaynah Javed (UC Berkeley) · Satvik Sharma (UC Berkeley) · Jerry Zhu (UC Berkeley) · Marek Petrik (University of New Hampshire) · Anca Dragan (University of California, Berkeley) · Ken Goldberg (UC Berkeley)

Online Learning with Optimism and Delay
Genevieve Flaspohler (Massachusetts Institute of Technology) · Francesco Orabona (Boston University) · Judah Cohen (AER) · Soukayna Mouatadid (University of Toronto) · Miruna Oprescu (Microsoft Research) · Paulo Orenstein (Instituto de Matemática Pura e Aplicada) · Lester Mackey (Microsoft Research)

Latent Programmer: Discrete Latent Codes for Program Synthesis
Joey Hong (Google) · David Dohan (Google) · Rishabh Singh (Google Brain) · Charles Sutton (Google) · Manzil Zaheer (Google Research)

Toward Better Generalization Bounds with Locally Elastic Stability
Zhun Deng (Harvard) · Hangfeng He (University of Pennsylvania) · Weijie Su (University of Pennsylvania)

Reinforcement Learning of Implicit and Explicit Control Flow Instructions
Ethan Brooks (University of Michigan) · Janarthanan Rajendran (University of Michigan) · Richard Lewis (University of Michigan) · Satinder Singh (University of Michigan)

Integrated Defense for Resilient Graph Matching
Jiaxiang Ren (Auburn University) · Zijie Zhang (Auburn University) · Jiayin Jin (Auburn University) · Xin Zhao (Auburn University) · Sixing Wu (Peking University) · Yang Zhou (Auburn University) · Yelong Shen (Microsoft Dynamics 365 AI) · Tianshi Che (Auburn University) · Ruoming Jin (Kent State University) · Dejing Dou (" University of Oregon, USA")

Adaptive Newton Sketch: Linear-time Optimization with Quadratic Convergence and Effective Hessian Dimensionality
Jonathan Lacotte (Stanford University) · Yifei Wang (Stanford University) · Mert Pilanci (Stanford)

Understanding the Dynamics of Gradient Flow in Overparameterized Linear models
Salma Tarmoun (Johns Hopkins University) · Guilherme Franca (UC Berkeley) · Benjamin Haeffele (Johns Hopkins University) · Rene Vidal (Johns Hopkins University, USA)

Accuracy, Interpretability, and Differential Privacy via Explainable Boosting
Harsha Nori (Microsoft) · Rich Caruana (Microsoft) · Zhiqi Bu (University of Pennsylvania) · Judy Hanwen Shen (Stanford) · Janardhan Kulkarni (Microsoft Research)

Neural Pharmacodynamic State Space Modeling
Zeshan Hussain (MIT) · Rahul G. Krishnan (Microsoft Research) · David Sontag (Massachusetts Institute of Technology)

SCC: an efficient deep reinforcement learning agent mastering the game of StarCraft II
Xiangjun Wang (inspir.ai) · Junxiao SONG (inspir.ai) · Penghui Qi (InspirAI) · Peng Peng (inspir.ai) · Zhenkun Tang (inspir.ai) · Wei Zhang (inspir.ai) · Weimin Li (inspir.ai) · Xiongjun Pi (inspir.ai) · Jujie He (inspir.ai) · Chao Gao (inspir.ai) · Haitao Long (inspir.ai) · Quan Yuan (inspir.ai)

A Hessian-free Interior-point Method for Non-convex Bilevel Optimization
Risheng Liu (Dalian University of Technology) · Xuan Liu (Dalian University of Technology) · Xiaoming Yuan (The University of Hong Kong) · Shangzhi Zeng (The University of Hong Kong) · Jin Zhang (Southern University of Science and Technology)

Elastic Graph Neural Networks
Xiaorui Liu (Michigan State University) · Wei Jin (Michigan State University) · Yao Ma (Michigan State University) · Yaxin Li (Michigan State University) · Hua Liu (Shandong University ) · Yiqi Wang (Michigan State University) · Ming Yan (Michigan State University) · Jiliang Tang (Michigan State University)

To be Robust or to be Fair: Towards Fairness in Adversarial Training
Han Xu (Michigan State University) · Xiaorui Liu (Michigan State University) · Yaxin Li (Michigan State University) · Jiliang Tang (Michigan State University) · Anil Jain (Michigan State University)

Implicit rate-constrained optimization of non-decomposable objectives
Abhishek Kumar (Google Brain) · Harikrishna Narasimhan (Google Research) · Andrew Cotter (Google AI)

Reinforcement Learning Under Moral Uncertainty
Adrien Ecoffet (OpenAI) · Joel Lehman ()

Data augmentation for deep learning based accelerated MRI reconstruction with limited data
Zalan Fabian (USC) · Reinhard Heckel (TUM) · Mahdi Soltanolkotabi (University of Southern California)

Fold2Seq: A Joint Sequence(1D)-Fold(3D) Embedding-based Generative Model for Protein Design
yue cao (Texas A&M University) · Payel Das (IBM Research AI) · Vijil Chenthamarakshan (IBM Research) · Pin-Yu Chen (IBM Research AI) · Igor Melnyk (IBM) · Yang Shen (Texas A&M University)

PipeTransformer: Automated Elastic Pipelining for Distributed Training of Transformers
Chaoyang He (University of Southern California (SSO)) · Shen Li (Facebook AI Applied Research) · Mahdi Soltanolkotabi (University of Southern California) · Salman Avestimehr (University of Southern California)

CURI: A Benchmark for Productive Concept Learning Under Uncertainty
Shanmukha Ramakrishna Vedantam (Facebook AI Research) · Arthur Szlam (Facebook) · Maximilian Nickel (Facebook AI Research) · Ari Morcos (Facebook AI Research) · Brenden Lake (New York University)

Debiasing Model Updates for Improving Personalized Federated Training
Durmus Alp Emre Acar (Boston University) · Yue Zhao (Arm Research) · Ruizhao Zhu (Boston University) · Ramon Matas (arm) · Matthew Mattina (ARM Research) · Paul Whatmough (Arm Research) · Venkatesh Saligrama (Boston University)

When Does Data Augmentation Help With Membership Inference Attacks?
Yigitcan Kaya (University of Maryland, College Park) · Tudor Dumitras (University of Maryland)

Poolingformer: Long Document Modeling with Pooling Attention
Hang ZHANG (College of Computer Science, Sichuan University) · Yeyun Gong (Microsoft Research Asia) · Yelong Shen (microsoft) · Weisheng Li (University of Science and Technology of China) · Nan Duan (Microsoft Research) · Weizhu Chen (Microsoft) · Jiancheng Lv (Sichuan University)

Adversarial Multi Class Learning under Weak Supervision with Performance Guarantees
Alessio Mazzetto (Brown University) · Cyrus Cousins (Brown University) · Dylan Sam (Brown University) · Eli Upfal (Brown University) · Stephen Bach (Brown University)

Causality-aware counterfactual confounding adjustment as an alternative to linear residualization in anticausal prediction tasks based on linear learners
Elias Chaibub Neto (Sage Bionetworks)

Learning from Nested Data with Ornstein Auto-Encoders
Youngwon Choi (University of California, Los Angeles) · Sungdong Lee (Seoul National University) · Joong-Ho Won (Seoul National University)

Towards Understanding and Mitigating Social Biases in Language Models
Paul Liang (CMU) · Chiyu Wu (Carnegie Mellon University) · Louis-Philippe Morency (Carnegie Mellon University) · Ruslan Salakhutdinov (Carnegie Mellen University)

Locally Persistent Exploration in Continuous Control Tasks with Sparse Rewards
Susan Amin (McGill University) · Maziar Gomrokchi (McGill University / Mila) · Hossein Aboutalebi (University of Waterloo) · Harsh Satija (McGill University) · Doina Precup (McGill University / DeepMind)

Leveraging Public Data for Practical Private Query Release
Terrance Liu (Carnegie Mellon University) · Giuseppe Vietri (University of Minnesota) · Thomas Steinke (Google) · Jonathan Ullman (Northeastern University) · Steven Wu (Carnegie Mellon University)

Conservative Objective Models for Effective Offline Model-Based Optimization
Brandon L Trabucco (UC Berkeley) · Aviral Kumar (UC Berkeley) · Xinyang Geng (UC Berkeley) · Sergey Levine (UC Berkeley)

Randomized Algorithms for Submodular Function Maximization with a $k$-System Constraint
Shuang Cui (University of Science and Technology of China) · Kai Han (University of Science and Technology of China) · Tianshuai Zhu (University of Science and Technology of China) · Jing Tang (The Hong Kong University of Science and Technology) · Benwei Wu (University of Science and Technology of China) · He Huang (Soochow University)

Learning While Playing in Mean-Field Games: Convergence and Optimality
Qiaomin Xie (Cornell University) · Zhuoran Yang (Princeton University) · Zhaoran Wang (Northwestern U) · Andreea Minca (Cornell University)

Z-GCNETs: Time Zigzags at Graph Convolutional Networks for Time Series Forecasting
Yuzhou Chen (Southern Methodist University) · Ignacio Segovia (University of Texas at Dallas) · Yulia R Gel (University of Texas at Dallas)

State Relevance for Off-Policy Evaluation
Simon Shen (Harvard University) · Yecheng Ma (University of Pennsylvania) · Omer Gottesman (Harvard University) · Finale Doshi-Velez (Harvard University)

On Recovering from Modeling Errors Using Testing Bayesian Networks
Haiying Huang (UCLA) · Adnan Darwiche (UCLA)

Accelerating Feedforward Computation via Parallel Nonlinear Equation Solving
Yang Song (Stanford University) · Chenlin Meng (Stanford University) · Renjie Liao (University of Toronto) · Stefano Ermon (Stanford University)

Householder Sketch for Accurate and Accelerated Least-Mean-Squares Solvers
Jyotikrishna Dass (Texas A&M University) · Rabi Mahapatra (Texas A&M University)

Of Moments and Matching: Trade-offs and Treatments in Imitation Learning
Gokul Swamy (Carnegie Mellon University) · Sanjiban Choudhury (Aurora) · Steven Wu (Carnegie Mellon University) · J. Bagnell (Aurora Innovation)

Efficient Iterative Amortized Inference for Learning Symmetric and Disentangled Multi-Object Representations
Patrick Emami (University of Florida) · Pan He (University of Florida) · Sanjay Ranka (University of Florida) · Anand Rangarajan (University of Florida)

Testing DNN-based Autonomous Driving Systems under Critical Environmental Conditions
Zhong Li (Nanjing University) · Minxue Pan (Nanjing University) · Tian Zhang (Nanjing University) · Xuandong Li (Nanjing University)

A Zeroth-Order Block Coordinate Descent Algorithm for Huge-Scale Black-Box Optimization
HanQin Cai (UCLA) · Yuchen Lou (The University of Hong Kong) · Daniel Mckenzie (UCLA) · Wotao Yin (Alibaba US, DAMO Academy)

Model Performance Scaling with Multiple Data Sources
Tatsunori Hashimoto (Stanford)

A Scalable Second Order Method for Ill-Conditioned Matrix Completion from Few Samples
Christian Kümmerle (Johns Hopkins University) · Claudio Mayrink Verdun (Technical University of Munich)

On the Inherent Regularization Effects of Noise Injection During Training
Oussama Dhifallah (Harvard University) · Yue Lu (Harvard University, USA)

Label-Only Membership Inference Attacks
Christopher A. Choquette-Choo (Google) · Florian Tramer (Stanford University) · Nicholas Carlini (Google) · Nicolas Papernot (University of Toronto and Vector Institute)

Learn2Hop: Learned Optimization on Rough Landscapes
Amil Merchant (Google) · Luke Metz (Google Brain) · Samuel Schoenholz (Google Brain) · Ekin Cubuk (Google Brain)

One for One, or All for All: Equilibria and Optimality of Collaboration in Federated Learning
Avrim Blum (Toyota Technological Institute of Chicago) · Nika Haghtalab (University of California, Berkeley) · Richard Lanas Phillips (Cornell University) · Han Shao (Toyota Technological Institute at Chicago)

Failure Modes and Opportunities in Out-of-distribution Detection with Deep Generative Models
Lily Zhang (New York University) · Mark Goldstein (New York University) · Rajesh Ranganath (New York University)

Lottery Ticket Preserves Weight Correlation: Is It Desirable or Not?
Ning Liu (Midea Group) · Geng Yuan (Northeastern University) · Zhengping Che (Didi Chuxing) · Xuan Shen (Northeastern University) · Xiaolong Ma (Northeastern University) · Qing Jin (Northeastern University) · Jian Ren (Snap Inc.) · Jian Tang (AI Innovation Center, Midea Group) · Sijia Liu (Michigan State University) · Yanzhi Wang (Northeastern University)

Poisson-Randomised DirBN: Large Mutation is Needed in Dirichlet Belief Networks
Xuhui Fan (University of New South Wales) · Bin Li (Fudan University) · Yaqiong Li (UTS) · Scott SIsson (University of New South Wales, Sydney)

Non-Autoregressive Electron Redistribution Modeling for Reaction Prediction
Hangrui Bi (Peking University) · Hengyi Wang (Peking University) · Chence Shi (University of Montreal) · Connor Coley (MIT) · Jian Tang (HEC Montreal & MILA) · Hongyu Guo (National Research Council Canada)

Zero-Shot Text-to-Image Generation
Aditya Ramesh (OpenAI) · Mikhail Pavlov (OpenAI) · Gabriel Goh (OpenAI) · Scott Gray (OpenAI) · Chelsea Voss (OpenAI) · Alec Radford (OpenAI) · Mark Chen (OpenAI) · Ilya Sutskever (OpenAI)

Fairness of Exposure in Stochastic Bandits
Lequn Wang (Cornell University) · Wen Sun (Cornell University) · Thorsten Joachims (Cornell) · Yiwei Bai (Cornell University)

Trajectory Diversity for Zero-Shot Coordination
Andrei Lupu (Mila, McGill University) · Brandon Cui (Facebook AI Research) · Hengyuan Hu (Facebook AI Research) · Jakob Foerster (Facebook AI Research)

LIME: Learning Inductive Bias for Primitives of Mathematical Reasoning
Yuhuai Wu (University of Toronto) · Markus Rabe (Google) · Wenda Li (University of Cambridge) · Jimmy Ba (University of Toronto) · Roger Grosse (University of Toronto and Vector Institute) · Christian Szegedy (Google)

Smooth $p$-Wasserstein Distance: Structure, Empirical Approximation, and Statistical Applications
Sloan Nietert (Cornell University) · Ziv Goldfeld (Cornell University) · Kengo Kato (Cornell University)

Robust Density Estimation from Batches: The Best Things in Life are (Nearly) Free
Ayush Jain (UC San Diego) · Alon Orlitsky (UCSD)

A Theory of Label Propagation for Subpopulation Shift
Tianle Cai (Princeton University) · Ruiqi Gao (Princeton University) · Jason Lee (Princeton) · Qi Lei (Princeton University)

ActNN: Reducing Training Memory Footprint via 2-Bit Activation Compressed Training
Jianfei Chen (University of California, Berkeley) · Lianmin Zheng (UC Berkeley) · Zhewei Yao (University of California, Berkeley) · Dequan Wang (UC Berkeley) · Ion Stoica (UC Berkeley) · Michael Mahoney (UC Berkeley) · Joseph E Gonzalez (UC Berkeley)

Improved, Deterministic Smoothing for L_1 Certified Robustness
Alexander Levine (University of Maryland) · Soheil Feizi (University of Maryland)

Temporal Predictive Coding For Model-Based Planning In Latent Space
Tung Nguyen (VinAI Research) · Rui Shu (Stanford University) · Tuan Pham (VinAI Research) · Hung Bui (VinAI Research) · Stefano Ermon (Stanford University)

Temporally Correlated Task Scheduling for Sequence Learning
Xueqing Wu (University of Science and Technology of China) · Lewen Wang (Microsoft Research Asia) · Yingce Xia (Microsoft Research Asia) · Weiqing Liu (Microsoft Research) · Lijun Wu (Microsoft Research) · Shufang Xie (Microsoft Research Asia) · Tao Qin (Microsoft Research Asia) · Tie-Yan Liu (Microsoft Research Asia)

Solving Inverse Problems with a Flow-based Noise Model
Jay Whang (The University of Texas at Austin) · Qi Lei (Princeton University) · Alexandros Dimakis (UT Austin)

Network Inference and Influence Maximization from Samples
Wei Chen (Microsoft) · Xiaoming Sun (Institute of Computing Technology, Chinese Academy of Sciences ) · Jialin Zhang (Institute of Computing Technology, CAS) · Zhijie Zhang (Institute of Computing Technology, Chinese Academy of Sciences)

Learner-Private Online Convex Optimization
Jiaming Xu (Duke University) · Kuang Xu (Stanford University) · Dana Yang (Duke University)

Leveraging Non-uniformity in First-order Non-convex Optimization
Jincheng Mei (University of Alberta / Google Brain) · Yue Gao (University of Alberta) · Bo Dai (Google Brain) · Csaba Szepesvari (DeepMind/University of Alberta) · Dale Schuurmans (University of Alberta)

Collaborative Bayesian Optimization with Fair Regret
Rachael Hwee Ling Sim (National University of Singapore) · Yehong Zhang (Peng Cheng Laboratory) · Bryan Kian Hsiang Low (National University of Singapore) · Patrick Jaillet (MIT)

Composing Normalizing Flows for Inverse Problems
Jay Whang (The University of Texas at Austin) · Erik Lindgren (Google Research) · Alexandros Dimakis (UT Austin)

LTL2Action: Generalizing LTL Instructions for Multi-Task RL
Pashootan Vaezipoor (University of Toronto and Vector Institute) · Andrew C Li (University of Toronto and Vector Institute) · Rodrigo A Toro Icarte (University of Toronto and Vector Institute) · Sheila McIlraith (University of Toronto and Vector Institute)

Learning Transferable Visual Models From Natural Language Supervision
Alec Radford (OpenAI) · Jong Wook Kim (OpenAI) · Chris Hallacy (OpenAI) · Aditya Ramesh (OpenAI) · Gabriel Goh (OpenAI) · Sandhini Agarwal (OpenAI) · Girish Sastry (OpenAI) · Amanda Askell (Open AI) · Pamela Mishkin (OpenAI) · Jack Clark (OpenAI) · Gretchen Krueger (OpenAI) · Ilya Sutskever (OpenAI)

RNN with particle flow for probabilistic spatio-temporal forecasting
Soumyasundar Pal (McGill University) · Liheng Ma (McGill University) · Yingxue Zhang (Huawei Technologies Canada) · Mark Coates (McGill University)

How Sensitive is Offline RL to Distribution Shift?
Ruosong Wang (Carnegie Mellon University) · Yifan Wu (Carnegie Mellon University) · Sham Kakade (University of Washington) · Ruslan Salakhutdinov (Carnegie Mellen University)

On Learnability via Gradient Method for Two-Layer ReLU Neural Networks in Teacher-Student Setting
Shunta Akiyama (The University of Tokyo) · Taiji Suzuki (The University of Tokyo / RIKEN)

CRFL: Certifiably Robust Federated Learning against Backdoor Attacks
Chulin Xie (University of Illinois at Urbana-Champaign) · Pin-Yu Chen (IBM Research AI) · Minghao Chen (Zhejiang University) · Bo Li (UIUC)

Federated Learning under Arbitrary Communication Patterns
Dmitrii Avdiukhin (Indiana University, Bloomington) · Shiva Kasiviswanathan (Amazon)

A large-scale benchmark for few-shot program induction and synthesis
Ferran Alet (MIT) · Javier Lopez-Contreras (MIT) · James Koppel (MIT) · Maxwell Nye (MIT) · Armando Solar-Lezama (MIT) · Tomas Lozano-Perez (MIT) · Leslie Kaelbling ((organization)) · Josh Tenenbaum (MIT)

Hierarchical Agglomerative Graph Clustering in Nearly Linear Time
Laxman Dhulipala (Google Research) · David Eisenstat (Google) · Jakub Łącki (Google) · Vahab Mirrokni (Google Research) · Jessica Shi (MIT)

Private Adaptive Gradient Methods for Convex Optimization
Hilal Asi (Stanford University) · John Duchi (Stanford University) · Alireza Fallah (MIT) · Omid Javidbakht (Apple) · Kunal Talwar (Apple)

Targeted Data Acquisition for Evolving Negotiation Agents
Minae Kwon (Stanford University) · Siddharth Karamcheti (Stanford University) · Mariano-Florentino Cuellar (Stanford University) · Dorsa Sadigh (Stanford University)

BASE Layers: Simplifying Training of Large, Sparse Models
Mike Lewis (Facebook) · Shruti Bhosale (Facebook Inc, 1 Hacker Way, Menlo Park, CA 94025, United States) · Tim Dettmers (University of Washington) · Naman Goyal (Facebook Inc) · Luke Zettlemoyer (University of Washington)

Fixed-Parameter and Approximation Algorithms for PCA with Outliers
Yogesh Dahiya (The Institute of Mathematical Sciences (HBNI), Chennai, India) · Fedor Fomin (University of Bergen) · Kirill Simonov (University of Bergen) · Fahad Panolan (Indian Institute of Technology Hyderabad)

Rate-Distortion Analysis of Minimum Excess Risk in Bayesian Learning
Hassan Hafez-Kolahi (Sharif University of Technology) · Behrad Moniri (Sharif University of Technology) · Shohreh Kasaei (Sharif University of Technology) · Mahdieh Soleymani Baghshah (Sharif University of Technology)

Inferring Latent Dynamics Underlying Neural Population Activity via Neural Differential Equations
Timothy Kim (Princeton University) · Thomas Luo (Princeton University) · Jonathan Pillow (Princeton University) · Carlos Brody (Princeton University)

Sinkhorn Label Allocation: Semi-Supervised Classification via Annealed Self-Training
Kai Sheng Tai (Stanford University) · Peter Bailis (Stanford University) · Gregory Valiant (Stanford University)

Overcoming Catastrophic Forgetting by Bayesian Generative Regularization
PEI-HUNG Chen (UCLA) · Wei Wei (Google) · Cho-Jui Hsieh (UCLA) · Bo Dai (Google Brain)

Deep Coherent Exploration For Continuous Control
Yijie Zhang (University of Copenhagen) · Herke van Hoof (University of Amsterdam)

Mixed Cross Entropy Loss for Neural Machine Translation
haoran li (SUTD) · Wei Lu (Singapore University of Technology and Design)

KNAS: Green Neural Architecture Search
Jingjing Xu (ByteDance AI Lab) · Liang Zhao (Peking Unviersity) · Junyang Lin (Alibaba Group) · Rundong Gao (Tsinghua University) · Xu SUN (Peking University) · Hongxia Yang (Alibaba Group)

Intermediate Layer Optimization for Inverse Problems using Deep Generative Models
Giannis Daras (NTUA) · Joseph Dean (UT Austin) · Ajil Jalal (University of Texas at Austin) · Alexandros Dimakis (UT Austin)

LARNet: Lie Algebra Residual Network for Profile Face Recognition
Xiaolong Yang (AMSS,CAS) · Xiaohong Jia (Chinese Academy of Sciences) · Dihong Gong (Tencent) · Dong-Ming Yan (NLPR, CASIA) · Zhifeng Li (Tencent AI Lab) · Wei Liu (Tencent AI Lab)

Progressive-Scale Boundary Blackbox Attack via Projective Gradient Estimation
Jiawei Zhang (Zhejiang University) · Linyi Li (UIUC) · Huichen Li (University of Illinois at Urbana-Champaign) · Xiaolu Zhang (Ant Financial Services Group) · Shuang Yang (Ant Financial) · Bo Li (UIUC)

Online Submodular Resource Allocation with Applications to Rebalancing Shared Mobility Systems
Pier Giuseppe Sessa (ETH Zürich) · Ilija Bogunovic (ETH Zurich) · Andreas Krause (ETH Zurich) · Maryam Kamgarpour (ETH Zürich)

Size-Invariant Graph Representations for Graph Classification Extrapolations
Beatrice Bevilacqua (Purdue University) · Yangze Zhou (Purdue University) · Bruno Ribeiro (Purdue University)

See the Future through the Void: Active Pre-Training with Successor Features
Hao Liu (UC Berkeley) · Pieter Abbeel (UC Berkeley & Covariant)

Accuracy on the Line: on the Strong Correlation Between Out-of-Distribution and In-Distribution Generalization
John Miller (University of California, Berkeley) · Rohan Taori (Stanford University) · Aditi Raghunathan (Stanford) · Shiori Sagawa (Stanford University) · Pang Wei Koh (Stanford University) · Vaishaal Shankar (UC Berkeley) · Percy Liang (Stanford University) · Yair Carmon (Tel Aviv University) · Ludwig Schmidt (Toyota Research Institute)

Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech
Jaehyeon Kim (Kakao Enterprise) · Jungil Kong (Kakao Enterprise) · Juhee Son (Kakao Enterprise)

Dense for the Price of Sparse: Improved Performance of Sparsely Initialized Networks via a Subspace Offset
Ilan Price (University of Oxford) · Jared Tanner (Oxford University)

Generative Particle Variational Inference via Estimation of Functional Gradients
Neale Ratzlaff (Oregon State University) · Qinxun Bai (Horizon Robotics) · Fuxin Li (Oregon State University) · Wei Xu (Horizon Robotics)

Fast margin maximization via dual acceleration
Ziwei Ji (University of Illinois at Urbana-Champaign) · Nati Srebro (Toyota Technological Institute at Chicago) · Matus Telgarsky (UIUC)

Learning Fair Policies in Decentralized Cooperative Multi-Agent Reinforcement Learning
Matthieu Zimmer (Shanghai Jiao Tong University) · Claire Glanois (Shanghai Jiao Tong University) · Umer Siddique (Shanghai Jiao Tong University) · Paul Weng (Shanghai Jiao Tong University)

Chebyshev Polynomial Codes: Task Entanglement-based Coding for Distributed Matrix Multiplication
Sangwoo Hong (Seoul National University) · Heecheol Yang (Chungnam National University) · Youngseok Yoon (Seoul National University) · Tae Hyun Cho (Seoul National University) · Jungwoo Lee (Seoul National University)

Online Algorithm Selection: A Rested Bandit Formulation
Leonardo Cella (Italian Institute of Technology) · Claudio Gentile (Google Research) · Massimiliano Pontil (Istituto Italiano di Tecnologia and University College London)

Training Quantized Neural Networks to Global Optimality via Semidefinite Programming
Burak Bartan (Stanford University) · Mert Pilanci (Stanford)

ASAM: Adaptive Sharpness-Aware Minimization for Scale-Invariant Optimization of Deep Neural Networks
Jungmin Kwon (Samsung Research) · Jeongseop Kim (Samsung Research) · Hyunseo Park (Samsung Research) · In Kwon Choi (Samsung Research)

Neural Architecture Search without Training
Joe Mellor (University of Edinburgh) · Jack Turner (University of Edinburgh) · Amos Storkey (University of Edinburgh) · Elliot Crowley (University of Edinburgh)

Meta-learning Hyperparameter Performance Prediction with Neural Processes
Ying WEI (City University of Hong Kong) · Peilin Zhao (Tencent AI Lab) · Junzhou Huang (University of Texas at Arlington / Tencent AI Lab)

Leveraging Good Representations in Linear Contextual Bandits
Matteo Papini (Universitat Pompeu Fabra) · Andrea Tirinzoni (Inria) · Marcello Restelli (Politecnico di Milano) · Alessandro Lazaric (Facebook AI Research) · Matteo Pirotta (Facebook AI Research)

FOP: Factorizing Optimal Joint Policy of Maximum-Entropy Multi-Agent Reinforcement Learning
Tianhao Zhang (Peking University) · yueheng li (Peking university) · Chen Wang (Peking University) · Zongqing Lu (Peking University) · Guangming Xie (1. State Key Laboratory for Turbulence and Complex Systems, College of Engineering, Peking University; 2. Institute of Ocean Research, Peking University)

Decomposing lexical, compositional, syntactic, and semantic operations in the brain through the lens of deep language models
charlotte caucheteux (INRIA Saclay) · Alexandre Gramfort (Inria) · Jean-Remi King (CNRS)

Learning Binary Decision Trees by Argmin Differentiation
Valentina Zantedeschi (INRIA, UCL) · Matt J. Kusner (University College London) · Vlad Niculae (Instituto de Telecomunicações // NIF 502854200)

Provably Efficient Fictitious Play Policy Optimization for Zero-Sum Markov Games with Structured Transitions
Shuang Qiu (University of Michigan) · Zhuoran Yang (Princeton University) · Xiaohan Wei (Facebook) · Jieping Ye (University of Michigan) · Zhaoran Wang (Northwestern U)

Improving Ultrametrics Embeddings Through Coresets
Vincent Cohen-Addad (Google, Switzerland) · Rémi de Joannis de Verclos (Radboud University) · Guillaume Lagarde (LaBRI)

Scalable Optimal Transport in High Dimensions for Graph Distances, Embedding Alignment, and More
Johannes Klicpera (Technical University Munich) · Marten Lienen (Technical University of Munich) · Stephan Günnemann (Technical University of Munich)

Locally Adaptive Label Smoothing Improves Predictive Churn
Dara Bahri (Google Research) · Heinrich Jiang (Google Research)

On Reward-Free RL with Kernel and Neural Function Approximations: Single-Agent MDP and Markov Game
Shuang Qiu (University of Michigan) · Zhuoran Yang (Princeton University) · Jieping Ye (University of Michigan) · Zhaoran Wang (Northwestern U)

Grey-box Extraction of Natural Language Models
Santiago Zanella-Beguelin (Microsoft Research) · Shruti Tople (Microsoft Research) · Andrew Paverd (Microsoft Research) · Boris Köpf (Microsoft Research)

On the Problem of Underranking in Group-Fair Ranking
Sruthi Gorantla (Indian Institute of Science) · Amit Jayant Deshpande (Microsoft Research) · Anand Louis (Indian Institute of Science, Bangalore, India)

Mind the box: $l_1$-APGD for sparse adversarial attacks on image classifiers
Francesco Croce (University of Tuebingen) · Matthias Hein (University of Tübingen)

TFix: Learning to Fix Coding Errors with a Text-to-Text Transformer
Berkay Berabi (ETH Zurich) · Jingxuan He (ETH Zurich) · Veselin Raychev (Snyk) · Martin Vechev (ETH Zurich)

Generating images with sparse representations
Charlie Nash (DeepMind) · Jacob Menick (DeepMind) · Sander Dieleman (DeepMind) · Peter Battaglia (DeepMind)

Value-at-Risk Optimization with Gaussian Processes
Quoc Phong Nguyen (National University of Singapore) · Zhongxiang Dai (National University of Singapore) · Bryan Kian Hsiang Low (National University of Singapore) · Patrick Jaillet (MIT)

Uniform Convergence and Infinite Width
Gregor Bachmann (ETH Zurich) · Seyed-Mohsen Moosavi-Dezfooli (ETH Zurich) · Thomas Hofmann (ETH Zurich)

Graph Neural Networks Inspired by Classical Iterative Algorithms
Yang Yongyi (Fudan University) · Tang Liu (Fudan University) · Yangkun Wang (SJTU) · Jinjing Zhou (Amazon) · Quan Gan (Amazon) · Zhewei Wei (Renmin University of China) · Zheng Zhang (Amazon) · Zengfeng Huang (Fudan University) · David Wipf (Microsoft Research)

Meta Latents Learning for Open-World Recommender Systems
Qitian Wu (Shanghai Jiao Tong University) · Hengrui Zhang (University of Illinois at Chicago) · Xiaofeng Gao (Shanghai Jiaotong University) · Junchi Yan (Shanghai Jiao Tong University) · Hongyuan Zha (Shenzhen Institute of Artificial Intelligence and Robotics for Society; The Chinese University of Hong Kong, Shenzhen)

How rotational invariance of common kernels prevents generalization in high dimensions
Konstantin Donhauser (ETH Zürich) · Mingqi Wu (ETH Zurich) · Fanny Yang (ETH)

Narrow Margins: Classification, Margins and Fat Tails
Francois Buet-Golfouse (UCL)

Learning de-identified representations of prosody from raw audio
Jack Weston (Novoic) · Raphael Lenain (Novoic) · Udeepa Meepegama (Novoic) · Emil Fristed (Novoic Ltd)

Exploiting structured data for learning contagious diseases under incomplete testing
Maggie Makar (MIT) · Lauren R West (MGH) · David C Hooper (Massachusetts General Hospital) · Eric Horvitz (MSR) · Erica Shenoy (MGH) · John Guttag (MIT)

Scaleable Certified Segmentation via Randomized Smoothing
Marc Fischer (ETH Zurich) · Maximilian Baader (ETH Zürich) · Martin Vechev (ETH Zurich)

Nonparametric Hamiltonian Monte Carlo
Carol Mak (University of Oxford) · Fabian Zaiser (University of Oxford) · Luke Ong (University of Oxford)