Skip to yearly menu bar Skip to main content


(166 events)   Timezone:  
The 2021 schedule is still incomplete
Toggle Poster Visibility
Oral
Tue Jul 20 05:00 AM -- 05:20 AM (PDT)
Scalable Computations of Wasserstein Barycenter via Input Convex Neural Networks
In Optimal Transport
Jiaojiao Fan · Amirhossein Taghvaei · Yongxin Chen
[ Paper ]
Oral
Tue Jul 20 05:00 AM -- 05:20 AM (PDT)
BORE: Bayesian Optimization by Density-Ratio Estimation
In Auto-ML and Optimization
Louis Chi-Chun Tiao · Aaron Klein · Matthias W Seeger · Edwin V Bonilla · Cedric Archambeau · Fabio Ramos
[ Paper ]
Oral
Tue Jul 20 05:00 AM -- 05:20 AM (PDT)
Attention is not all you need: pure attention loses rank doubly exponentially with depth
In Deep Learning Applications
Yihe Dong · Jean-Baptiste Cordonnier · Andreas Loukas
[ Paper ]
Oral
Tue Jul 20 05:00 AM -- 05:20 AM (PDT)
Scalable Evaluation of Multi-Agent Reinforcement Learning with Melting Pot
In Reinforcement Learning (Multi-agent)
Joel Z Leibo · Edgar Duenez-Guzman · Alexander Vezhnevets · John Agapiou · Peter Sunehag · Raphael Koster · Jayd Matyas · Charles Beattie · Igor Mordatch · Thore Graepel
[ Paper ]
Oral
Tue Jul 20 05:00 AM -- 05:20 AM (PDT)
Relative Positional Encoding for Transformers with Linear Complexity
In Deep Learning Architectures
Antoine Liutkus · Ondřej Cífka · Shih-Lun Wu · Umut Simsekli · Yi-Hsuan Yang · Gaël RICHARD
[ Paper ]
Oral
Tue Jul 20 05:00 AM -- 05:20 AM (PDT)
Optimal Complexity in Decentralized Training
In Optimization (Distributed)
Yucheng Lu · Christopher De Sa
[ Paper ]
Oral
Tue Jul 20 05:00 AM -- 05:20 AM (PDT)
Deeply-Debiased Off-Policy Interval Estimation
In Deep Reinforcement Learning 2
Chengchun Shi · Runzhe Wan · Victor Chernozhukov · Rui Song
[ Paper ]
Oral
Tue Jul 20 05:00 AM -- 05:20 AM (PDT)
Phasic Policy Gradient
In Deep Reinforcement Learning 1
Karl Cobbe · Jacob Hilton · Oleg Klimov · John Schulman
[ Paper ]
Oral
Tue Jul 20 05:00 AM -- 05:20 AM (PDT)
Size-Invariant Graph Representations for Graph Classification Extrapolations
In Graph Learning
Beatrice Bevilacqua · Yangze Zhou · Bruno Ribeiro
[ Paper ]
Oral
Tue Jul 20 06:00 AM -- 06:20 AM (PDT)
PAGE: A Simple and Optimal Probabilistic Gradient Estimator for Nonconvex Optimization
In Optimization 1
Zhize Li · Hongyan Bao · Xiangliang Zhang · Peter Richtarik
[ Paper ]
Oral
Tue Jul 20 06:00 AM -- 06:20 AM (PDT)
Oops I Took A Gradient: Scalable Sampling for Discrete Distributions
In Deep Generative Model 1
Will Grathwohl · Kevin Swersky · Milad Hashemi · David Duvenaud · Chris Maddison
[ Paper ]
Oral
Tue Jul 20 06:00 AM -- 06:20 AM (PDT)
Let's Agree to Degree: Comparing Graph Convolutional Networks in the Message-Passing Framework
In Deep Learning Theory 1
Floris Geerts · Filip Mazowiecki · Guillermo Perez
[ Paper ]
Oral
Tue Jul 20 06:00 AM -- 06:20 AM (PDT)
Risk-Sensitive Reinforcement Learning with Function Approximation: A Debiasing Approach
In Reinforcement Learning 1
Yingjie Fei · Zhuoran Yang · Zhaoran Wang
[ Paper ]
Oral
Tue Jul 20 06:00 AM -- 06:20 AM (PDT)
Principled Simplicial Neural Networks for Trajectory Prediction
In Deep Learning Algorithms 2
T. Mitchell Roddenberry · Nicholas Glaze · Santiago Segarra
[ Paper ]
Oral
Tue Jul 20 06:00 AM -- 06:20 AM (PDT)
Leveraging Sparse Linear Layers for Debuggable Deep Networks
In Deep Learning Algorithms 1
Eric Wong · Shibani Santurkar · Aleksander Madry
[ Paper ]
Oral
Tue Jul 20 06:00 AM -- 06:20 AM (PDT)
Neural Architecture Search without Training
In AutoML and Deep Architecture
Joe Mellor · Jack Turner · Amos Storkey · Elliot Crowley
[ Paper ]
Oral
Tue Jul 20 06:00 AM -- 06:20 AM (PDT)
What Are Bayesian Neural Network Posteriors Really Like?
In Deep Learning (Bayesian)
Pavel Izmailov · Sharad Vikram · Matthew Hoffman · Andrew Wilson
[ Paper ]
Oral
Tue Jul 20 06:00 AM -- 06:20 AM (PDT)
Variance Reduction via Primal-Dual Accelerated Dual Averaging for Nonsmooth Convex Finite-Sums
In Optimization (Convex) 1
Chaobing Song · Stephen Wright · Jelena Diakonikolas
[ Paper ]
Oral
Tue Jul 20 07:00 AM -- 07:20 AM (PDT)
Stability and Convergence of Stochastic Gradient Clipping: Beyond Lipschitz Continuity and Smoothness
In Optimization 2
Vien Mai · Mikael Johansson
[ Paper ]
Oral
Tue Jul 20 07:00 AM -- 07:20 AM (PDT)
OmniNet: Omnidirectional Representations from Transformers
In AutoML and Neural Network Architectures 1
Yi Tay · Mostafa Dehghani · Vamsi Aribandi · Jai Gupta · Philip Pham · Zhen Qin · Dara Bahri · Da-Cheng Juan · Don Metzler
[ Paper ]
Oral
Tue Jul 20 07:00 AM -- 07:20 AM (PDT)
Coach-Player Multi-agent Reinforcement Learning for Dynamic Team Composition
In Reinforcement Learning 2
Bo Liu · Qiang Liu · Peter Stone · Animesh Garg · Yuke Zhu · Anima Anandkumar
[ Paper ]
Oral
Tue Jul 20 07:00 AM -- 07:20 AM (PDT)
World Model as a Graph: Learning Latent Landmarks for Planning
In Reinforcement Learning and Planning 1
Lunjun Zhang · Ge Yang · Bradly Stadie
[ Paper ]
Oral
Tue Jul 20 07:00 AM -- 07:20 AM (PDT)
ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision
In Deep Learning Algorithms 3
Wonjae Kim · Bokyung Son · Ildoo Kim
[ Paper ]
Oral
Tue Jul 20 07:00 AM -- 07:20 AM (PDT)
Skill Discovery for Exploration and Planning using Deep Skill Graphs
In Reinforcement Learning and Planning 2
Akhil Bagaria · Jason Senthil · George Konidaris
[ Paper ]
Oral
Tue Jul 20 07:00 AM -- 07:20 AM (PDT)
Directional Graph Networks
In Deep Learning Algorithms 4
Dominique Beaini · Saro Passaro · Vincent Létourneau · Will Hamilton · Gabriele Corso · Pietro Lió
[ Paper ]
Oral
Tue Jul 20 07:00 AM -- 07:20 AM (PDT)
Not All Memories are Created Equal: Learning to Forget by Expiring
In Deep Learning 1
Sainbayar Sukhbaatar · Da JU · Spencer Poff · Stephen Roller · Arthur Szlam · Jason Weston · Angela Fan
[ Paper ]
Oral
Tue Jul 20 07:00 AM -- 07:20 AM (PDT)
Spectral Smoothing Unveils Phase Transitions in Hierarchical Variational Autoencoders
In Deep Generative Model 2
Adeel Pervez · Efstratios Gavves
[ Paper ]
Oral
Tue Jul 20 05:00 PM -- 05:20 PM (PDT)
A Tale of Two Efficient and Informative Negative Sampling Distributions
In Optimization and Algorithms 1
Shabnam Daghaghi · Tharun Medini · Nicholas Meisburger · Beidi Chen · Mengnan Zhao · Anshumali Shrivastava
[ Paper ]
Oral
Tue Jul 20 05:00 PM -- 05:20 PM (PDT)
Randomized Entity-wise Factorization for Multi-Agent Reinforcement Learning
In Reinforcement Learning 3
Shariq Iqbal · Christian Schroeder · Bei Peng · Wendelin Boehmer · Shimon Whiteson · Fei Sha
[ Paper ]
Oral
Tue Jul 20 05:00 PM -- 05:20 PM (PDT)
On the price of explainability for some clustering problems
In Optimization 3
Eduardo Laber · Lucas Murtinho
[ Paper ]
Oral
Tue Jul 20 05:00 PM -- 05:20 PM (PDT)
CATE: Computation-aware Neural Architecture Encoding with Transformers
In Deep Learning Algorithms 6
Shen Yan · Kaiqiang Song · Fei Liu · Mi Zhang
[ Paper ]
Oral
Tue Jul 20 05:00 PM -- 05:20 PM (PDT)
NeRF-VAE: A Geometry Aware 3D Scene Generative Model
In Deep Generative Model 3
Adam Kosiorek · Heiko Strathmann · Daniel Zoran · Pol Moreno · Rosalia Schneider · Sona Mokra · Danilo J. Rezende
[ Paper ]
Oral
Tue Jul 20 05:00 PM -- 05:20 PM (PDT)
A Practical Method for Constructing Equivariant Multilayer Perceptrons for Arbitrary Matrix Groups
In Deep Learning Algorithms 5
Marc Finzi · Max Welling · Andrew Wilson
[ Paper ]
Oral
Tue Jul 20 05:00 PM -- 05:20 PM (PDT)
Characterizing Structural Regularities of Labeled Data in Overparameterized Models
In Deep Learning 2
Ziheng Jiang · Chiyuan Zhang · Kunal Talwar · Michael Mozer
[ Paper ]
Oral
Tue Jul 20 05:00 PM -- 05:20 PM (PDT)
Robust Asymmetric Learning in POMDPs
In Reinforcement Learning 4
Andrew Warrington · Jonathan Lavington · Adam Scibior · Mark Schmidt · Frank Wood
[ Paper ]
Oral
Tue Jul 20 05:00 PM -- 05:20 PM (PDT)
PsiPhi-Learning: Reinforcement Learning with Demonstrations using Successor Features and Inverse Temporal Difference Learning
In Reinforcement Learning and Planning 3
Angelos Filos · Clare Lyle · Yarin Gal · Sergey Levine · Natasha Jaques · Gregory Farquhar
[ Paper ]
Oral
Tue Jul 20 06:00 PM -- 06:20 PM (PDT)
Unbiased Gradient Estimation in Unrolled Computation Graphs with Persistent Evolution Strategies
In Deep Learning Algorithms and Applications
Paul Vicol · Luke Metz · Jascha Sohl-Dickstein
[ Paper ]
Oral
Tue Jul 20 06:00 PM -- 06:20 PM (PDT)
The Power of Adaptivity for Stochastic Submodular Cover
In Optimization (Stochastic)
Rohan Ghuge · Anupam Gupta · viswanath nagarajan
[ Paper ]
Oral
Tue Jul 20 06:00 PM -- 06:20 PM (PDT)
PEBBLE: Feedback-Efficient Interactive Reinforcement Learning via Relabeling Experience and Unsupervised Pre-training
In Reinforcement Learning 7
Kimin Lee · Laura Smith · Pieter Abbeel
[ Paper ]
Oral
Tue Jul 20 06:00 PM -- 06:20 PM (PDT)
Network Inference and Influence Maximization from Samples
In Optimization and Algorithms 2
Wei Chen · Xiaoming Sun · Jialin Zhang · Zhijie Zhang
[ Paper ]
Oral
Tue Jul 20 06:00 PM -- 06:20 PM (PDT)
Decoupling Value and Policy for Generalization in Reinforcement Learning
In Reinforcement Learning 6
Roberta Raileanu · Rob Fergus
[ Paper ]
Oral
Tue Jul 20 06:00 PM -- 06:20 PM (PDT)
Generating images with sparse representations
In Deep Generative Model 4
Charlie Nash · Jacob Menick · Sander Dieleman · Peter Battaglia
[ Paper ]
Oral
Tue Jul 20 06:00 PM -- 06:20 PM (PDT)
The Emergence of Individuality
In Reinforcement Learning 5
Jiechuan Jiang · Zongqing Lu
[ Paper ]
Oral
Tue Jul 20 06:00 PM -- 06:20 PM (PDT)
A Wasserstein Minimax Framework for Mixed Linear Regression
In Algorithms 1
Theo Diamandis · Yonina Eldar · Alireza Fallah · Farzan Farnia · Asuman Ozdaglar
[ Paper ]
Oral
Tue Jul 20 06:15 PM -- 06:35 PM (PDT)
Few-Shot Neural Architecture Search
In AutoML
Yiyang Zhao · Linnan Wang · Yuandong Tian · Rodrigo Fonseca · Tian Guo
[ Paper ]
Oral
Tue Jul 20 07:00 PM -- 07:20 PM (PDT)
Accelerated Algorithms for Smooth Convex-Concave Minimax Problems with O(1/k^2) Rate on Squared Gradient Norm
In Optimization (Convex) 2
TaeHo Yoon · Ernest Ryu
[ Paper ]
Oral
Tue Jul 20 07:00 PM -- 07:20 PM (PDT)
Just Train Twice: Improving Group Robustness without Training Group Information
In Deep Learning Algorithms 8
Evan Liu · Behzad Haghgoo · Annie Chen · Aditi Raghunathan · Pang Wei Koh · Shiori Sagawa · Percy Liang · Chelsea Finn
[ Paper ]
Oral
Tue Jul 20 07:00 PM -- 07:20 PM (PDT)
AlphaNet: Improved Training of Supernets with Alpha-Divergence
In AutoML and Neural Network Architectures 2
Dilin Wang · Chengyue Gong · Meng Li · Qiang Liu · Vikas Chandra
[ Paper ]
Oral
Tue Jul 20 07:00 PM -- 07:20 PM (PDT)
Inverse Decision Modeling: Learning Interpretable Representations of Behavior
In Reinforcement Learning 8
Daniel Jarrett · Alihan Hüyük · Mihaela van der Schaar
[ Paper ]
Oral
Tue Jul 20 07:00 PM -- 07:20 PM (PDT)
Hyperparameter Selection for Imitation Learning
In Reinforcement Learning 9
Léonard Hussenot · Marcin Andrychowicz · Damien Vincent · Robert Dadashi · Anton Raichuk · Sabela Ramos · Nikola Momchev · Sertan Girgin · Raphael Marinier · Lukasz Stafiniak · Emmanuel Orsini · Olivier Bachem · Matthieu Geist · Olivier Pietquin
[ Paper ]
Oral
Tue Jul 20 07:00 PM -- 07:20 PM (PDT)
ActNN: Reducing Training Memory Footprint via 2-Bit Activation Compressed Training
In Large Scale Optimization
Jianfei Chen · Lianmin Zheng · Zhewei Yao · Dequan Wang · Ion Stoica · Michael Mahoney · Joseph E Gonzalez
[ Paper ]
Oral
Tue Jul 20 07:00 PM -- 07:20 PM (PDT)
Out-of-Distribution Generalization via Risk Extrapolation (REx)
In Deep Learning Algorithms 7
David Krueger · Ethan Caballero · Joern-Henrik Jacobsen · Amy Zhang · Jonathan Binas · Dinghuai Zhang · Remi Le Priol · Aaron Courville
[ Paper ]
Oral
Tue Jul 20 07:00 PM -- 07:20 PM (PDT)
Cooperative Exploration for Multi-Agent Deep Reinforcement Learning
In Deep Reinforcement Learning 3
Iou-Jen Liu · Unnat Jain · Raymond Yeh · Alex Schwing
[ Paper ]
Oral
Tue Jul 20 07:00 PM -- 07:20 PM (PDT)
Sequential Domain Adaptation by Synthesizing Distributionally Robust Experts
In Optimization 4
Bahar Taskesen · Man-Chung Yue · Jose Blanchet · Daniel Kuhn · Viet Anh Nguyen
[ Paper ]
Oral
Wed Jul 21 05:00 AM -- 05:20 AM (PDT)
APS: Active Pretraining with Successor Features
In Reinforcement Learning 11
Hao Liu · Pieter Abbeel
[ Paper ]
Oral
Wed Jul 21 05:00 AM -- 05:20 AM (PDT)
Improving Lossless Compression Rates via Monte Carlo Bits-Back Coding
In Probabilistic Methods 1
Yangjun Ruan · Karen Ullrich · Daniel Severo · James Townsend · Ashish Khisti · Arnaud Doucet · Alireza Makhzani · Chris Maddison
[ Paper ]
Oral
Wed Jul 21 05:00 AM -- 05:20 AM (PDT)
Robust Density Estimation from Batches: The Best Things in Life are (Nearly) Free
In Learning Theory 2
Ayush Jain · Alon Orlitsky
[ Paper ]
Oral
Wed Jul 21 05:00 AM -- 05:20 AM (PDT)
When All We Need is a Piece of the Pie: A Generic Framework for Optimizing Two-way Partial AUC
In Supervised Learning 1
Zhiyong Yang · Qianqian Xu · Shilong Bao · Yuan He · Xiaochun Cao · Qingming Huang
[ Paper ]
Oral
Wed Jul 21 05:00 AM -- 05:20 AM (PDT)
Optimizing persistent homology based functions
In Optimization (Nonconvex)
Mathieu Carrière · Frederic Chazal · Marc Glisse · Yuichi Ike · Hariprasad Kannan · Yuhei Umeda
[ Paper ]
Oral
Wed Jul 21 05:00 AM -- 05:20 AM (PDT)
On Energy-Based Models with Overparametrized Shallow Neural Networks
In Deep Learning Theory 2
Carles Domingo-Enrich · Alberto Bietti · Eric Vanden-Eijnden · Joan Bruna
[ Paper ]
Oral
Wed Jul 21 05:00 AM -- 05:20 AM (PDT)
Near Optimal Reward-Free Reinforcement Learning
In Learning Theory 1
Zhang Zihan · Simon Du · Xiangyang Ji
[ Paper ]
Oral
Wed Jul 21 05:00 AM -- 05:20 AM (PDT)
The Limits of Min-Max Optimization Algorithms: Convergence to Spurious Non-Critical Sets
In Learning Theory 3
Ya-Ping Hsieh · Panayotis Mertikopoulos · Volkan Cevher
[ Paper ]
Oral
Wed Jul 21 05:00 AM -- 05:20 AM (PDT)
Cross-domain Imitation from Observations
In Reinforcement Learning 10
Dripta S. Raychaudhuri · Sujoy Paul · Jeroen Vanbaar · Amit Roy-Chowdhury
[ Paper ]
Oral
Wed Jul 21 06:00 AM -- 06:20 AM (PDT)
Elastic Graph Neural Networks
In Algorithms and Applications
Xiaorui Liu · Wei Jin · Yao Ma · Yaxin Li · Hua Liu · Yiqi Wang · Ming Yan · Jiliang Tang
[ Paper ]
Oral
Wed Jul 21 06:00 AM -- 06:20 AM (PDT)
Provably Efficient Fictitious Play Policy Optimization for Zero-Sum Markov Games with Structured Transitions
In Reinforcement Learning and Optimization
Shuang Qiu · Xiaohan Wei · Jieping Ye · Zhaoran Wang · Zhuoran Yang
[ Paper ]
Oral
Wed Jul 21 06:00 AM -- 06:20 AM (PDT)
Reserve Price Optimization for First Price Auctions in Display Advertising
In Game Theory and Econ
Zhe Feng · Sébastien Lahaie · Jon Schneider · Jinchao Ye
[ Paper ]
Oral
Wed Jul 21 06:00 AM -- 06:20 AM (PDT)
Understanding Instance-Level Label Noise: Disparate Impacts and Treatments
In Supervised Learning 2
Yang Liu
[ Paper ]
Oral
Wed Jul 21 06:00 AM -- 06:20 AM (PDT)
Bilinear Classes: A Structural Framework for Provable Generalization in RL
In Reinforcement Learning Theory 1
Simon Du · Sham Kakade · Jason Lee · Shachar Lovett · Gaurav Mahajan · Wen Sun · Ruosong Wang
[ Paper ]
Oral
Wed Jul 21 06:00 AM -- 06:20 AM (PDT)
Model-based Reinforcement Learning for Continuous Control with Posterior Sampling
In Reinforcement Learning 12
Ying Fan · Yifei Ming
[ Paper ]
Oral
Wed Jul 21 06:00 AM -- 06:20 AM (PDT)
Agnostic Learning of Halfspaces with Gradient Descent via Soft Margins
In Learning Theory 4
Spencer Frei · Yuan Cao · Quanquan Gu
[ Paper ]
Oral
Wed Jul 21 06:00 AM -- 06:20 AM (PDT)
Dynamic Game Theoretic Neural Optimizer
In Optimization and Algorithms 3
Guan-Horng Liu · Tianrong Chen · Evangelos Theodorou
[ Paper ]
Oral
Wed Jul 21 06:00 AM -- 06:20 AM (PDT)
Regret and Cumulative Constraint Violation Analysis for Online Convex Optimization with Long Term Constraints
In Online Learning 1
Xinlei Yi · Xiuxian Li · Tao Yang · Lihua Xie · Tianyou Chai · Karl Johansson
[ Paper ]
Oral
Wed Jul 21 07:00 AM -- 07:20 AM (PDT)
PAC-Learning for Strategic Classification
In Learning Theory 6
Ravi Sundaram · Anil Vullikanti · Haifeng Xu · Fan Yao
[ Paper ]
Oral
Wed Jul 21 07:00 AM -- 07:20 AM (PDT)
The Logical Options Framework
In Reinforcement Learning 13
Brandon Araki · Xiao Li · Kiran Vodrahalli · Jonathan DeCastro · Micah Fry · Daniela Rus
[ Paper ]
Oral
Wed Jul 21 07:00 AM -- 07:20 AM (PDT)
High-dimensional Experimental Design and Kernel Bandits
In Bandits 1
Romain Camilleri · Kevin Jamieson · Julian Katz-Samuels
[ Paper ]
Oral
Wed Jul 21 07:00 AM -- 07:20 AM (PDT)
Inferring Latent Dynamics Underlying Neural Population Activity via Neural Differential Equations
In Applications (Bio) 1
Timothy Kim · Thomas Luo · Jonathan Pillow · Carlos Brody
[ Paper ]
Oral
Wed Jul 21 07:00 AM -- 07:20 AM (PDT)
On the Implicit Bias of Initialization Shape: Beyond Infinitesimal Mirror Descent
In Deep Learning Theory 3
Shahar Azulay · Edward Moroshko · Mor Shpigel Nacson · Blake Woodworth · Nati Srebro · Amir Globerson · Daniel Soudry
[ Paper ]
Oral
Wed Jul 21 07:00 AM -- 07:20 AM (PDT)
Inferring serial correlation with dynamic backgrounds
In Time Series 1
Song Wei · Yao Xie · Dobromir Rahnev
[ Paper ]
Oral
Wed Jul 21 07:00 AM -- 07:20 AM (PDT)
Measuring Robustness in Deep Learning Based Compressive Sensing
In Sparsity and Compressed Sensing
Mohammad Zalbagi Darestani · Akshay Chaudhari · Reinhard Heckel
[ Paper ]
Oral
Wed Jul 21 07:00 AM -- 07:20 AM (PDT)
Kernel Stein Discrepancy Descent
In Kernel Methods
Anna Korba · Pierre-Cyril Aubin-Frankowski · Szymon Majewski · Pierre Ablin
[ Paper ]
Oral
Wed Jul 21 07:00 AM -- 07:20 AM (PDT)
Modelling Behavioural Diversity for Learning in Open-Ended Games
In Learning Theory 5
Nicolas Perez-Nieves · Yaodong Yang · Oliver Slumbers · David Mguni · Ying Wen · Jun Wang
[ Paper ]
Oral
Wed Jul 21 07:20 AM -- 07:40 AM (PDT)
On Reward-Free RL with Kernel and Neural Function Approximations: Single-Agent MDP and Markov Game
In Reinforcement Learning 13
Shuang Qiu · Jieping Ye · Zhaoran Wang · Zhuoran Yang
[ Paper ]
Oral
Wed Jul 21 05:00 PM -- 05:20 PM (PDT)
Exponential Lower Bounds for Batch Reinforcement Learning: Batch RL can be Exponentially Harder than Online RL
In Reinforcement Learning Theory 2
Andrea Zanette
[ Paper ]
Oral
Wed Jul 21 05:00 PM -- 05:20 PM (PDT)
The Implicit Bias for Adaptive Optimization Algorithms on Homogeneous Neural Networks
In Deep Learning Theory 4
Bohan Wang · Qi Meng · Wei Chen · Tie-Yan Liu
[ Paper ]
Oral
Wed Jul 21 05:00 PM -- 05:20 PM (PDT)
UCB Momentum Q-learning: Correcting the bias without forgetting
In Reinforcement Learning Theory 3
Pierre Menard · Omar Darwiche Domingues · Xuedong Shang · Michal Valko
[ Paper ]
Oral
Wed Jul 21 05:00 PM -- 05:20 PM (PDT)
Online Unrelated Machine Load Balancing with Predictions Revisited
In Online Learning 2
Shi Li · Jiayi Xian
[ Paper ]
Oral
Wed Jul 21 05:00 PM -- 05:20 PM (PDT)
Label Distribution Learning Machine
In Supervised Learning 3
Jing Wang · Xin Geng
[ Paper ]
Oral
Wed Jul 21 05:00 PM -- 05:20 PM (PDT)
Understanding self-supervised learning dynamics without contrastive pairs
In Deep Learning Optimization
Yuandong Tian · Xinlei Chen · Surya Ganguli
[ Paper ]
Oral
Wed Jul 21 05:00 PM -- 05:20 PM (PDT)
Rate-Distortion Analysis of Minimum Excess Risk in Bayesian Learning
In Learning Theory 8
Hassan Hafez-Kolahi · Behrad Moniri · Shohreh Kasaei · Mahdieh Soleymani Baghshah
[ Paper ]
Oral
Wed Jul 21 05:00 PM -- 05:20 PM (PDT)
The Symmetry between Arms and Knapsacks: A Primal-Dual Approach for Bandits with Knapsacks
In Bandits 2
Xiaocheng Li · Chunlin Sun · Yinyu Ye
[ Paper ]
Oral
Wed Jul 21 05:00 PM -- 05:20 PM (PDT)
Learning Optimal Auctions with Correlated Valuations from Samples
In Learning Theory 7
CHUNXUE YANG · Xiaohui Bei
[ Paper ]
Oral
Wed Jul 21 06:00 PM -- 06:20 PM (PDT)
Cyclically Equivariant Neural Decoders for Cyclic Codes
In Learning Theory 9
Xiangyu Chen · Min Ye
[ Paper ]
Oral
Wed Jul 21 06:00 PM -- 06:20 PM (PDT)
Discriminative Complementary-Label Learning with Weighted Loss
In Supervised Learning 4
Yi Gao · Min-Ling Zhang
[ Paper ]
Oral
Wed Jul 21 06:00 PM -- 06:20 PM (PDT)
Task-Optimal Exploration in Linear Dynamical Systems
In Reinforcement Learning 14
Andrew Wagenmaker · Max Simchowitz · Kevin Jamieson
[ Paper ]
Oral
Wed Jul 21 06:00 PM -- 06:20 PM (PDT)
Resource Allocation in Multi-armed Bandit Exploration: Overcoming Sublinear Scaling with Adaptive Parallelism
In Bandits 3
Brijen Thananjeyan · Kirthevasan Kandasamy · Ion Stoica · Michael Jordan · Ken Goldberg · Joseph E Gonzalez
[ Paper ]
Oral
Wed Jul 21 06:00 PM -- 06:20 PM (PDT)
RATT: Leveraging Unlabeled Data to Guarantee Generalization
In Learning Theory 10
Saurabh Garg · Sivaraman Balakrishnan · Zico Kolter · Zachary Lipton
[ Paper ]
Oral
Wed Jul 21 06:00 PM -- 06:20 PM (PDT)
Provably Efficient Algorithms for Multi-Objective Competitive RL
In Reinforcement Learning Theory 4
Tiancheng Yu · Yi Tian · Jingzhao Zhang · Suvrit Sra
[ Paper ]
Oral
Wed Jul 21 06:00 PM -- 06:20 PM (PDT)
Stability and Generalization of Stochastic Gradient Methods for Minimax Problems
In Learning Theory 11
Yunwen Lei · Zhenhuan Yang · Tianbao Yang · Yiming Ying
[ Paper ]
Oral
Wed Jul 21 06:00 PM -- 06:20 PM (PDT)
Dissecting Supervised Constrastive Learning
In Deep Learning Theory 5
Florian Graf · Christoph Hofer · Marc Niethammer · Roland Kwitt
[ Paper ]
Oral
Wed Jul 21 06:00 PM -- 06:20 PM (PDT)
Conformal prediction interval for dynamic time-series
In Time Series 2
Chen Xu · Yao Xie
[ Paper ]
Oral
Wed Jul 21 07:00 PM -- 07:20 PM (PDT)
A Precise Performance Analysis of Support Vector Regression
In Learning Theory 12
Houssem Sifaou · Abla Kammoun · Mohamed-Slim Alouini
[ Paper ]
Oral
Wed Jul 21 07:00 PM -- 07:20 PM (PDT)
RNN with Particle Flow for Probabilistic Spatio-temporal Forecasting
In Applications 2
Soumyasundar Pal · Liheng Ma · Yingxue Zhang · Mark Coates
[ Paper ]
Oral
Wed Jul 21 07:00 PM -- 07:20 PM (PDT)
Break-It-Fix-It: Unsupervised Learning for Program Repair
In Applications 1
Michihiro Yasunaga · Percy Liang
[ Paper ]
Oral
Wed Jul 21 07:00 PM -- 07:20 PM (PDT)
Analysis of stochastic Lanczos quadrature for spectrum approximation
In Learning Theory 13
Tyler Chen · Thomas Trogdon · Shashanka Ubaru
[ Paper ]
Oral
Wed Jul 21 07:00 PM -- 07:20 PM (PDT)
Learning Gradient Fields for Molecular Conformation Generation
In Applications (Bio) 2
Chence Shi · Shitong Luo · Minkai Xu · Jian Tang
[ Paper ]
Oral
Wed Jul 21 07:00 PM -- 07:20 PM (PDT)
Multi-layered Network Exploration via Random Walks: From Offline Optimization to Online Learning
In Bandits 4
Xutong Liu · Jinhang Zuo · Xiaowei Chen · Wei Chen · John C. S. Lui
[ Paper ]
Oral
Wed Jul 21 07:00 PM -- 07:20 PM (PDT)
Improved Regret Bound and Experience Replay in Regularized Policy Iteration
In Reinforcement Learning Theory 5
Nevena Lazic · Dong Yin · Yasin Abbasi-Yadkori · Csaba Szepesvari
[ Paper ]
Oral
Wed Jul 21 07:00 PM -- 07:20 PM (PDT)
Can Subnetwork Structure Be the Key to Out-of-Distribution Generalization?
In Algorithms 2
Dinghuai Zhang · Kartik Ahuja · Yilun Xu · Yisen Wang · Aaron Courville
[ Paper ]
Oral
Wed Jul 21 07:00 PM -- 07:20 PM (PDT)
Multi-Dimensional Classification via Sparse Label Encoding
In Supervised Learning 6
BINBIN JIA · Min-Ling Zhang
[ Paper ]
Oral
Wed Jul 21 07:20 PM -- 07:40 PM (PDT)
Latent Programmer: Discrete Latent Codes for Program Synthesis
In Supervised Learning 6
Joey Hong · David Dohan · Rishabh Singh · Charles Sutton · Manzil Zaheer
[ Paper ]
Oral
Thu Jul 22 05:00 AM -- 05:20 AM (PDT)
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision
In Representation Learning 1
Chao Jia · Yinfei Yang · Ye Xia · Yi-Ting Chen · Zarana Parekh · Hieu Pham · Quoc Le · Yun-Hsuan Sung · Zhen Li · Tom Duerig
[ Paper ]
Oral
Thu Jul 22 05:00 AM -- 05:20 AM (PDT)
Fair Selective Classification Via Sufficiency
In Fairness
Joshua Lee · Yuheng Bu · Deepta Rajan · Prasanna Sattigeri · Rameswar Panda · Subhro Das · Gregory Wornell
[ Paper ]
Oral
Thu Jul 22 05:00 AM -- 05:20 AM (PDT)
Local Algorithms for Finding Densely Connected Clusters
In Unsupervised Learning 1
Peter Macgregor · He Sun
[ Paper ]
Oral
Thu Jul 22 05:00 AM -- 05:20 AM (PDT)
Differentiable Particle Filtering via Entropy-Regularized Optimal Transport
In Probabilistic Methods 2
Adrien Corenflos · James Thornton · George Deligiannidis · Arnaud Doucet
[ Paper ]
Oral
Thu Jul 22 05:00 AM -- 05:20 AM (PDT)
Coded-InvNet for Resilient Prediction Serving Systems
In Systems and Hardware
Tuan Dinh · Kangwook Lee
[ Paper ]
Oral
Thu Jul 22 05:00 AM -- 05:20 AM (PDT)
Confidence Scores Make Instance-dependent Label-noise Learning Possible
In Semisupervised Learning 1
Antonin Berthon · Bo Han · Gang Niu · Tongliang Liu · Masashi Sugiyama
[ Paper ]
Oral
Thu Jul 22 05:00 AM -- 05:20 AM (PDT)
Tighter Bounds on the Log Marginal Likelihood of Gaussian Process Regression Using Conjugate Gradients
In Gaussian Processes 1
Artem Artemev · David Burt · Mark van der Wilk
[ Paper ]
Oral
Thu Jul 22 05:00 AM -- 05:20 AM (PDT)
Tilting the playing field: Dynamical loss functions for machine learning
In Deep Learning Theory 6
Miguel Ruiz Garcia · Ge Zhang · Samuel Schoenholz · Andrea Liu
[ Paper ]
Oral
Thu Jul 22 05:00 AM -- 05:20 AM (PDT)
Modularity in Reinforcement Learning via Algorithmic Independence in Credit Assignment
In Reinforcement Learning 15
Michael Chang · Sid Kaushik · Sergey Levine · Thomas Griffiths
[ Paper ]
Oral
Thu Jul 22 06:00 AM -- 06:20 AM (PDT)
Temporal Difference Learning as Gradient Splitting
In Learning Theory 14
Rui Liu · Alex Olshevsky
[ Paper ]
Oral
Thu Jul 22 06:00 AM -- 06:20 AM (PDT)
Delving into Deep Imbalanced Regression
In Applications and Algorithms
Yuzhe Yang · Kaiwen Zha · YINGCONG CHEN · Hao Wang · Dina Katabi
[ Paper ]
Oral
Thu Jul 22 06:00 AM -- 06:20 AM (PDT)
Learning Noise Transition Matrix from Only Noisy Labels via Total Variation Regularization
In Semisupervised Learning 2
Yivan Zhang · Gang Niu · Masashi Sugiyama
[ Paper ]
Oral
Thu Jul 22 06:00 AM -- 06:20 AM (PDT)
Dash: Semi-Supervised Learning with Dynamic Thresholding
In Semisupervised Learning 3
Yi Xu · Lei Shang · Jinxing Ye · Qi Qian · Yu-Feng Li · Baigui Sun · Hao Li · rong jin
[ Paper ]
Oral
Thu Jul 22 06:00 AM -- 06:20 AM (PDT)
I-BERT: Integer-only BERT Quantization
In Applications (NLP) 1
Sehoon Kim · Amir Gholaminejad · Zhewei Yao · Michael Mahoney · EECS Kurt Keutzer
[ Paper ]
Oral
Thu Jul 22 06:00 AM -- 06:20 AM (PDT)
Benchmarks, Algorithms, and Metrics for Hierarchical Disentanglement
In Representation Learning 2
Andrew Ross · Finale Doshi-Velez
[ Paper ]
Oral
Thu Jul 22 06:00 AM -- 06:20 AM (PDT)
Differentially Private Query Release Through Adaptive Projection
In Privacy 1
Sergul Aydore · William Brown · Michael Kearns · Krishnaram Kenthapadi · Luca Melis · Aaron Roth · Ankit Siva
[ Paper ]
Oral
Thu Jul 22 06:00 AM -- 06:20 AM (PDT)
Deep Adaptive Design: Amortizing Sequential Bayesian Experimental Design
In Bayesian Learning 1
Adam Foster · Desi Ivanova · ILYAS MALIK · Tom Rainforth
[ Paper ]
Oral
Thu Jul 22 06:00 AM -- 06:20 AM (PDT)
Improved, Deterministic Smoothing for L_1 Certified Robustness
In Adversarial Learning 1
Alexander Levine · Soheil Feizi
[ Paper ]
Oral
Thu Jul 22 07:00 AM -- 07:20 AM (PDT)
Locally Private k-Means in One Round
In Privacy 2
Alisa Chang · Badih Ghazi · Ravi Kumar · Pasin Manurangsi
[ Paper ]
Oral
Thu Jul 22 07:00 AM -- 07:20 AM (PDT)
Graph Contrastive Learning Automated
In Semisupervised and Unsupervised Learning 1
Yuning You · Tianlong Chen · Yang Shen · Zhangyang “Atlas” Wang
[ Paper ]
Oral
Thu Jul 22 07:00 AM -- 07:20 AM (PDT)
Annealed Flow Transport Monte Carlo
In Bayesian Methods
Michael Arbel · Alexander Matthews · Arnaud Doucet
[ Paper ]
Oral
Thu Jul 22 07:00 AM -- 07:20 AM (PDT)
Modeling Hierarchical Structures with Continuous Recursive Neural Networks
In Applications (CV and NLP)
Jishnu Ray Chowdhury · Cornelia Caragea
[ Paper ]
Oral
Thu Jul 22 07:00 AM -- 07:20 AM (PDT)
Domain Generalization using Causal Matching
In Domain Generalization and Multi-task Learning
Divyat Mahajan · Shruti Tople · Amit Sharma
[ Paper ]
Oral
Thu Jul 22 07:00 AM -- 07:20 AM (PDT)
DG-LMC: A Turn-key and Scalable Synchronous Distributed MCMC Algorithm via Langevin Monte Carlo within Gibbs
In Probabilistic Methods 3
Vincent Plassier · Maxime Vono · Alain Durmus · Eric Moulines
[ Paper ]
Oral
Thu Jul 22 07:00 AM -- 07:20 AM (PDT)
Private Alternating Least Squares: Practical Private Matrix Completion with Tighter Rates
In Privacy 3
Steve Chien · Prateek Jain · Walid Krichene · Steffen Rendle · Shuang Song · Abhradeep Guha Thakurta · Li Zhang
[ Paper ]
Oral
Thu Jul 22 07:00 AM -- 07:20 AM (PDT)
CARTL: Cooperative Adversarially-Robust Transfer Learning
In Adversarial Learning 2
Dian Chen · Hongxin Hu · Qian Wang · Li Yinli · Cong Wang · Chao Shen · Qi Li
[ Paper ]
Oral
Thu Jul 22 07:00 AM -- 07:20 AM (PDT)
On Disentangled Representations Learned from Correlated Data
In Representation Learning 3
Frederik Träuble · Elliot Creager · Niki Kilbertus · Francesco Locatello · Andrea Dittadi · Anirudh Goyal · Bernhard Schölkopf · Stefan Bauer
[ Paper ]
Oral
Thu Jul 22 05:00 PM -- 05:20 PM (PDT)
Leveraged Weighted Loss for Partial Label Learning
In Semisupervised and Unsupervised Learning 2
Hongwei Wen · Jingyi Cui · Hanyuan Hang · Jiabin Liu · Yisen Wang · Zhouchen Lin
[ Paper ]
Oral
Thu Jul 22 05:00 PM -- 05:20 PM (PDT)
Global Prosody Style Transfer Without Text Transcriptions
In Applications (NLP) 2
Kaizhi Qian · Yang Zhang · Shiyu Chang · Jinjun Xiong · Chuang Gan · David Cox · Mark Hasegawa-Johnson
[ Paper ]
Oral
Thu Jul 22 05:00 PM -- 05:20 PM (PDT)
Composed Fine-Tuning: Freezing Pre-Trained Denoising Autoencoders for Improved Generalization
In Multi-task Learning 1
Sang Michael Xie · Tengyu Ma · Percy Liang
[ Paper ]
Oral
Thu Jul 22 05:00 PM -- 05:20 PM (PDT)
Gradient Disaggregation: Breaking Privacy in Federated Learning by Reconstructing the User Participant Matrix
In Security and Explanability
Maximilian Lam · Gu-Yeon Wei · David Brooks · Vijay Janapa Reddi · Michael Mitzenmacher
[ Paper ]
Oral
Thu Jul 22 05:00 PM -- 05:20 PM (PDT)
Probabilistic Generating Circuits
In Probabilistic Methods 4
Honghua Zhang · Brendan Juba · Guy Van den Broeck
[ Paper ]
Oral
Thu Jul 22 05:00 PM -- 05:20 PM (PDT)
Commutative Lie Group VAE for Disentanglement Learning
In Representation Learning 4
Xinqi Zhu · Chang Xu · Dacheng Tao
[ Paper ]
Oral
Thu Jul 22 05:00 PM -- 05:20 PM (PDT)
Straight to the Gradient: Learning to Use Novel Tokens for Neural Text Generation
In Applications 3
Xiang Lin · Simeng Han · Shafiq Joty
[ Paper ]
Oral
Thu Jul 22 05:00 PM -- 05:20 PM (PDT)
Exponential Reduction in Sample Complexity with Learning of Ising Model Dynamics
In Bayesian Learning 2
Arkopal Dutt · Andrey Lokhov · Marc Vuffray · Sidhant Misra
[ Paper ]
Oral
Thu Jul 22 05:00 PM -- 05:20 PM (PDT)
Sparse and Imperceptible Adversarial Attack via a Homotopy Algorithm
In Adversarial Learning 3
Mingkang Zhu · Tianlong Chen · Zhangyang “Atlas” Wang
[ Paper ]
Oral
Thu Jul 22 06:00 PM -- 06:20 PM (PDT)
Solving high-dimensional parabolic PDEs using the tensor train format
In Probabilistic Methods 5
Lorenz Richter · Leon Sallandt · Nikolas Nüsken
[ Paper ]
Oral
Thu Jul 22 06:00 PM -- 06:20 PM (PDT)
Private Stochastic Convex Optimization: Optimal Rates in L1 Geometry
In Privacy 4
Hilal Asi · Vitaly Feldman · Tomer Koren · Kunal Talwar
[ Paper ]
Oral
Thu Jul 22 06:00 PM -- 06:20 PM (PDT)
Dimensionality Reduction for the Sum-of-Distances Metric
In Unsupervised Learning 2
Zhili Feng · Praneeth Kacham · David Woodruff
[ Paper ]
Oral
Thu Jul 22 06:00 PM -- 06:20 PM (PDT)
Learn-to-Share: A Hardware-friendly Transfer Learning Framework Exploiting Computation and Parameter Sharing
In Algorithms 4
Cheng Fu · Hanxian Huang · Xinyun Chen · Yuandong Tian · Jishen Zhao
[ Paper ]
Oral
Thu Jul 22 06:00 PM -- 06:20 PM (PDT)
Unsupervised Representation Learning via Neural Activation Coding
In Representation Learning 5
Yookoon Park · Sangho Lee · Gunhee Kim · David Blei
[ Paper ]
Oral
Thu Jul 22 06:00 PM -- 06:20 PM (PDT)
WILDS: A Benchmark of in-the-Wild Distribution Shifts
In Multi-task Learning 2
Pang Wei Koh · Shiori Sagawa · Henrik Marklund · Sang Michael Xie · Marvin Zhang · Akshay Balsubramani · Weihua Hu · Michihiro Yasunaga · Richard Lanas Phillips · Irena Gao · Tony Lee · Etienne David · Ian Stavness · Wei Guo · Berton Earnshaw · Imran Haque · Sara Beery · Jure Leskovec · Anshul Kundaje · Emma Pierson · Sergey Levine · Chelsea Finn · Percy Liang
[ Paper ]
Oral
Thu Jul 22 06:00 PM -- 06:20 PM (PDT)
Integer Programming for Causal Structure Learning in the Presence of Latent Variables
In Algorithms 3
Rui Chen · Sanjeeb Dash · Tian Gao
[ Paper ]
Oral
Thu Jul 22 06:00 PM -- 06:20 PM (PDT)
Label Inference Attacks from Log-loss Scores
In Security
Abhinav Aggarwal · Shiva Kasiviswanathan · Zekun Xu · Oluwaseyi Feyisetan · Nathanael Teissier
[ Paper ]
Oral
Thu Jul 22 06:00 PM -- 06:20 PM (PDT)
Calibrate Before Use: Improving Few-shot Performance of Language Models
In Applications (NLP) 3
Tony Z. Zhao · Eric Wallace · Shi Feng · Dan Klein · Sameer Singh
[ Paper ]
Oral
Thu Jul 22 07:00 PM -- 07:20 PM (PDT)
Learning Transferable Visual Models From Natural Language Supervision
In Multi-modal and Meta Learning
Alec Radford · Jong Wook Kim · Chris Hallacy · Aditya Ramesh · Gabriel Goh · Sandhini Agarwal · Girish Sastry · Amanda Askell · Pamela Mishkin · Jack Clark · Gretchen Krueger · Ilya Sutskever
[ Paper ]
Oral
Thu Jul 22 07:00 PM -- 07:20 PM (PDT)
Differentially Private Sliced Wasserstein Distance
In Privacy 5
alain rakotomamonjy · Ralaivola Liva
[ Paper ]
Oral
Thu Jul 22 07:00 PM -- 07:20 PM (PDT)
Graph Cuts Always Find a Global Optimum for Potts Models (With a Catch)
In Probabilistic Methods 6
Hunter Lang · David Sontag · Aravindan Vijayaraghavan
[ Paper ]
Oral
Thu Jul 22 07:00 PM -- 07:20 PM (PDT)
A General Framework For Detecting Anomalous Inputs to DNN Classifiers
In Adversarial Learning 4
Jayaram Raghuram · Varun Chandrasekaran · Somesh Jha · Suman Banerjee
[ Paper ]
Oral
Thu Jul 22 07:00 PM -- 07:20 PM (PDT)
Additive Error Guarantees for Weighted Low Rank Approximation
In Unsupervised Learning 4
Aditya Bhaskara · Aravinda Kanchana Ruwanpathirana · Pruthuvi Maheshakya Wijewardena
[ Paper ]
Oral
Thu Jul 22 07:00 PM -- 07:20 PM (PDT)
Correlation Clustering in Constant Many Parallel Rounds
In Unsupervised Learning 3
Vincent Cohen-Addad · Silvio Lattanzi · Slobodan Mitrović · Ashkan Norouzi-Fard · Nikos Parotsidis · Jakub Tarnawski
[ Paper ]
Oral
Thu Jul 22 07:00 PM -- 07:20 PM (PDT)
Order-Agnostic Cross Entropy for Non-Autoregressive Machine Translation
In Applications (NLP) 4
Cunxiao Du · Zhaopeng Tu · Jing Jiang
[ Paper ]
Oral
Thu Jul 22 07:00 PM -- 07:20 PM (PDT)
Graph Neural Networks Inspired by Classical Iterative Algorithms
In Representation Learning 6
Yang Yongyi · Tang Liu · Yangkun Wang · Jinjing Zhou · Quan Gan · Zhewei Wei · Zheng Zhang · Zengfeng Huang · David Wipf
[ Paper ]
Oral
Thu Jul 22 07:00 PM -- 07:20 PM (PDT)
Crowdsourcing via Annotator Co-occurrence Imputation and Provable Symmetric Nonnegative Matrix Factorization
In Unsupervised Learning 5
Shahana Ibrahim · Xiao Fu
[ Paper ]
Oral
Thu Jul 22 07:20 PM -- 07:40 PM (PDT)
SKIing on Simplices: Kernel Interpolation on the Permutohedral Lattice for Scalable Gaussian Processes
In Probabilistic Methods 6
Sanyam Kapoor · Marc Finzi · Ke Alexander Wang · Andrew Wilson
[ Paper ]
Oral
Thu Jul 22 07:20 PM -- 07:40 PM (PDT)
Mixed Cross Entropy Loss for Neural Machine Translation
In Applications (NLP) 4
Haoran Li · Wei Lu
[ Paper ]