Filter by Keyword:

265 Results

Affinity Workshop
Mon 9:15 OCDE: Odds Conditional Density Estimator
Alex Aki Okuno, Felipe Polo
Tutorial
Mon 12:00 Random Matrix Theory and ML (RMT+ML)
Fabian Pedregosa, Courtney Paquette, Thomas Trogdon, Jeffrey Pennington
Affinity Workshop
Mon 15:15 A Tree-Adaptation Mechanism for Covariate and Concept Drift
Leno Silva, Renato Vicente
Oral
Tue 5:00 Deeply-Debiased Off-Policy Interval Estimation
Chengchun Shi, Runzhe Wan, Victor Chernozhukov, Rui Song
Oral Session
Tue 6:00 Deep Learning Theory 1
Spotlight
Tue 6:25 A Probabilistic Approach to Neural Network Pruning
Xin Qian, Diego Klabjan
Spotlight
Tue 6:35 A Functional Perspective on Learning Symmetric Functions with Neural Networks
Aaron Zweig, Joan Bruna
Spotlight
Tue 7:20 Tesseract: Tensorised Actors for Multi-Agent Reinforcement Learning
Anuj Mahajan, Mikayel Samvelyan, Lei Mao, Viktor Makoviychuk, Animesh Garg, Jean Kossaifi, Shimon Whiteson, Yuke Zhu, Anima Anandkumar
Spotlight
Tue 7:20 Learning Bounds for Open-Set Learning
Zhen Fang, Jie Lu, Anjin Liu, Feng Liu, Guangquan Zhang
Poster
Tue 9:00 Deeply-Debiased Off-Policy Interval Estimation
Chengchun Shi, Runzhe Wan, Victor Chernozhukov, Rui Song
Poster
Tue 9:00 Learning Bounds for Open-Set Learning
Zhen Fang, Jie Lu, Anjin Liu, Feng Liu, Guangquan Zhang
Poster
Tue 9:00 Decoupling Value and Policy for Generalization in Reinforcement Learning
Roberta Raileanu, Rob Fergus
Poster
Tue 9:00 A Probabilistic Approach to Neural Network Pruning
Xin Qian, Diego Klabjan
Poster
Tue 9:00 Tesseract: Tensorised Actors for Multi-Agent Reinforcement Learning
Anuj Mahajan, Mikayel Samvelyan, Lei Mao, Viktor Makoviychuk, Animesh Garg, Jean Kossaifi, Shimon Whiteson, Yuke Zhu, Anima Anandkumar
Poster
Tue 9:00 A Functional Perspective on Learning Symmetric Functions with Neural Networks
Aaron Zweig, Joan Bruna
Oral
Tue 18:00 Decoupling Value and Policy for Generalization in Reinforcement Learning
Roberta Raileanu, Rob Fergus
Spotlight
Tue 18:30 LAMDA: Label Matching Deep Domain Adaptation
Trung Le, Tuan Nguyen, Nhat Ho, Hung Bui, Dinh Phung
Poster
Tue 21:00 LAMDA: Label Matching Deep Domain Adaptation
Trung Le, Tuan Nguyen, Nhat Ho, Hung Bui, Dinh Phung
Oral Session
Wed 5:00 Learning Theory 3
Oral Session
Wed 5:00 Deep Learning Theory 2
Oral
Wed 5:00 Robust Density Estimation from Batches: The Best Things in Life are (Nearly) Free
Ayush Jain, Alon Orlitsky
Oral
Wed 5:00 On Energy-Based Models with Overparametrized Shallow Neural Networks
Carles Domingo-Enrich, Alberto Bietti, Eric Vanden-Eijnden, Joan Bruna
Oral Session
Wed 5:00 Learning Theory 1
Oral Session
Wed 5:00 Learning Theory 2
Spotlight
Wed 5:20 Uncertainty Principles of Encoding GANs
TaiGe Feng, Zhouchen Lin, jiapeng zhu, Deli Zhao, Jingren Zhou, Zheng-Jun Zha
Spotlight
Wed 5:20 Theory of Spectral Method for Union of Subspaces-Based Random Geometry Graph
Gen Li, Yuantao Gu
Spotlight
Wed 5:20 Generalization Bounds in the Presence of Outliers: a Median-of-Means Study
Pierre Laforgue, Guillaume Staerman, Stephan Clémençon
Spotlight
Wed 5:25 On the Proof of Global Convergence of Gradient Descent for Deep ReLU Networks with Linear Widths
Quynh Nguyen
Spotlight
Wed 5:25 Approximating a Distribution Using Weight Queries
Nadav Barak, Sivan Sabato
Spotlight
Wed 5:25 Adversarial Combinatorial Bandits with General Non-linear Reward Functions
Yanjun Han, Yining Wang, Xi Chen
Spotlight
Wed 5:25 Meta Learning for Support Recovery in High-dimensional Precision Matrix Estimation
Qian Zhang, Yilin Zheng, Jean Honorio
Spotlight
Wed 5:30 Tight Bounds on the Smallest Eigenvalue of the Neural Tangent Kernel for Deep ReLU Networks
Quynh Nguyen, Marco Mondelli, Guido Montufar
Spotlight
Wed 5:30 Robust Inference for High-Dimensional Linear Models via Residual Randomization
Y. Samuel Wang, Si Kai Lee, Panos Toulis, Mladen Kolar
Spotlight
Wed 5:35 Functional Space Analysis of Local GAN Convergence
Valentin Khrulkov, Artem Babenko, Ivan Oseledets
Spotlight
Wed 5:35 Don’t Just Blame Over-parametrization for Over-confidence: Theoretical Analysis of Calibration in Binary Classification
Yu Bai, Song Mei, Huan Wang, Caiming Xiong
Spotlight
Wed 5:40 Generalization Guarantees for Neural Architecture Search with Train-Validation Split
Samet Oymak, Mingchen Li, Mahdi Soltanolkotabi
Spotlight
Wed 5:40 Exact Gap between Generalization Error and Uniform Convergence in Random Feature Models
Zitong Yang, Yu Bai, Song Mei
Spotlight
Wed 5:40 On Learnability via Gradient Method for Two-Layer ReLU Neural Networks in Teacher-Student Setting
Shunta Akiyama, Taiji Suzuki
Spotlight
Wed 5:45 Provable Generalization of SGD-trained Neural Networks of Any Width in the Presence of Adversarial Label Noise
Spencer Frei, Yuan Cao, Quanquan Gu
Spotlight
Wed 5:45 Optimal Estimation of High Dimensional Smooth Additive Function Based on Noisy Observations
Fan Zhou, Ping Li
Oral
Wed 6:00 Agnostic Learning of Halfspaces with Gradient Descent via Soft Margins
Spencer Frei, Yuan Cao, Quanquan Gu
Oral Session
Wed 6:00 Learning Theory 4
Oral Session
Wed 6:00 Reinforcement Learning Theory 1
Spotlight
Wed 6:20 Two-way kernel matrix puncturing: towards resource-efficient PCA and spectral clustering
Romain COUILLET, Florent Chatelain, Nicolas Le Bihan
Spotlight
Wed 6:20 Risk Bounds and Rademacher Complexity in Batch Reinforcement Learning
Yaqi Duan, Chi Jin, Zhiyuan Li
Spotlight
Wed 6:25 A Lower Bound for the Sample Complexity of Inverse Reinforcement Learning
Abi Komanduru, Jean Honorio
Spotlight
Wed 6:30 Towards Open Ad Hoc Teamwork Using Graph-based Policy Learning
Arrasy Rahman, Niklas Hopner, Filippos Christianos, Stefano V. Albrecht
Spotlight
Wed 6:30 Estimation and Quantization of Expected Persistence Diagrams
Vincent Divol, Theo Lacombe
Spotlight
Wed 6:35 Post-selection inference with HSIC-Lasso
Tobias Freidling, Benjamin Poignard, Héctor Climente-González, Makoto Yamada
Spotlight
Wed 6:40 Provable Robustness of Adversarial Training for Learning Halfspaces with Noise
Difan Zou, Spencer Frei, Quanquan Gu
Spotlight
Wed 6:45 An Algorithm for Stochastic and Adversarial Bandits with Switching Costs
Chloé Rouyer, Yevgeny Seldin, Nicolò Cesa-Bianchi
Spotlight
Wed 6:45 Distribution-Free Calibration Guarantees for Histogram Binning without Sample Splitting
Chirag Gupta, Aaditya Ramdas
Oral
Wed 7:00 Inferring serial correlation with dynamic backgrounds
Song Wei, Yao Xie, Dobromir Rahnev
Oral Session
Wed 7:00 Learning Theory 5
Oral Session
Wed 7:00 Deep Learning Theory 3
Oral Session
Wed 7:00 Learning Theory 6
Oral
Wed 7:00 On the Implicit Bias of Initialization Shape: Beyond Infinitesimal Mirror Descent
Shahar Azulay, Edward Moroshko, Mor Shpigel Nacson, Blake Woodworth, Nati Srebro, Amir Globerson, Daniel Soudry
Spotlight
Wed 7:20 A statistical perspective on distillation
Aditya Menon, Ankit Singh Rawat, Sashank Jakkam Reddi, Seungyeon Kim, Sanjiv Kumar
Spotlight
Wed 7:25 The Lipschitz Constant of Self-Attention
Hyunjik Kim, George Papamakarios, Andriy Mnih
Spotlight
Wed 7:30 Guarantees for Tuning the Step Size using a Learning-to-Learn Approach
Xiang Wang, Shuai Yuan, Chenwei Wu, Rong Ge
Spotlight
Wed 7:30 Revealing the Structure of Deep Neural Networks via Convex Duality
Tolga Ergen, Mert Pilanci
Spotlight
Wed 7:35 Representational aspects of depth and conditioning in normalizing flows
Frederic Koehler, Viraj Mehta, Andrej Risteski
Spotlight
Wed 7:40 Toward Understanding the Feature Learning Process of Self-supervised Contrastive Learning
Zixin Wen, Yuanzhi Li
Spotlight
Wed 7:45 The Hintons in your Neural Network: a Quantum Field Theory View of Deep Learning
Roberto Bondesan, Max Welling
Poster
Wed 9:00 Uncertainty Principles of Encoding GANs
TaiGe Feng, Zhouchen Lin, jiapeng zhu, Deli Zhao, Jingren Zhou, Zheng-Jun Zha
Poster
Wed 9:00 Adversarial Combinatorial Bandits with General Non-linear Reward Functions
Yanjun Han, Yining Wang, Xi Chen
Poster
Wed 9:00 Approximating a Distribution Using Weight Queries
Nadav Barak, Sivan Sabato
Poster
Wed 9:00 Toward Understanding the Feature Learning Process of Self-supervised Contrastive Learning
Zixin Wen, Yuanzhi Li
Poster
Wed 9:00 Theory of Spectral Method for Union of Subspaces-Based Random Geometry Graph
Gen Li, Yuantao Gu
Poster
Wed 9:00 Inferring serial correlation with dynamic backgrounds
Song Wei, Yao Xie, Dobromir Rahnev
Poster
Wed 9:00 The Lipschitz Constant of Self-Attention
Hyunjik Kim, George Papamakarios, Andriy Mnih
Poster
Wed 9:00 Don’t Just Blame Over-parametrization for Over-confidence: Theoretical Analysis of Calibration in Binary Classification
Yu Bai, Song Mei, Huan Wang, Caiming Xiong
Poster
Wed 9:00 Generalization Bounds in the Presence of Outliers: a Median-of-Means Study
Pierre Laforgue, Guillaume Staerman, Stephan Clémençon
Poster
Wed 9:00 On the Proof of Global Convergence of Gradient Descent for Deep ReLU Networks with Linear Widths
Quynh Nguyen
Poster
Wed 9:00 Tight Bounds on the Smallest Eigenvalue of the Neural Tangent Kernel for Deep ReLU Networks
Quynh Nguyen, Marco Mondelli, Guido Montufar
Poster
Wed 9:00 Provable Robustness of Adversarial Training for Learning Halfspaces with Noise
Difan Zou, Spencer Frei, Quanquan Gu
Poster
Wed 9:00 Guarantees for Tuning the Step Size using a Learning-to-Learn Approach
Xiang Wang, Shuai Yuan, Chenwei Wu, Rong Ge
Poster
Wed 9:00 A statistical perspective on distillation
Aditya Menon, Ankit Singh Rawat, Sashank Jakkam Reddi, Seungyeon Kim, Sanjiv Kumar
Poster
Wed 9:00 Robust Inference for High-Dimensional Linear Models via Residual Randomization
Y. Samuel Wang, Si Kai Lee, Panos Toulis, Mladen Kolar
Poster
Wed 9:00 On Learnability via Gradient Method for Two-Layer ReLU Neural Networks in Teacher-Student Setting
Shunta Akiyama, Taiji Suzuki
Poster
Wed 9:00 Meta Learning for Support Recovery in High-dimensional Precision Matrix Estimation
Qian Zhang, Yilin Zheng, Jean Honorio
Poster
Wed 9:00 Robust Density Estimation from Batches: The Best Things in Life are (Nearly) Free
Ayush Jain, Alon Orlitsky
Poster
Wed 9:00 An Algorithm for Stochastic and Adversarial Bandits with Switching Costs
Chloé Rouyer, Yevgeny Seldin, Nicolò Cesa-Bianchi
Poster
Wed 9:00 Representational aspects of depth and conditioning in normalizing flows
Frederic Koehler, Viraj Mehta, Andrej Risteski
Poster
Wed 9:00 Optimal Estimation of High Dimensional Smooth Additive Function Based on Noisy Observations
Fan Zhou, Ping Li
Poster
Wed 9:00 Estimation and Quantization of Expected Persistence Diagrams
Vincent Divol, Theo Lacombe
Poster
Wed 9:00 Post-selection inference with HSIC-Lasso
Tobias Freidling, Benjamin Poignard, Héctor Climente-González, Makoto Yamada
Poster
Wed 9:00 A Lower Bound for the Sample Complexity of Inverse Reinforcement Learning
Abi Komanduru, Jean Honorio
Poster
Wed 9:00 Generalization Guarantees for Neural Architecture Search with Train-Validation Split
Samet Oymak, Mingchen Li, Mahdi Soltanolkotabi
Poster
Wed 9:00 Revealing the Structure of Deep Neural Networks via Convex Duality
Tolga Ergen, Mert Pilanci
Poster
Wed 9:00 Exact Gap between Generalization Error and Uniform Convergence in Random Feature Models
Zitong Yang, Yu Bai, Song Mei
Poster
Wed 9:00 Distribution-Free Calibration Guarantees for Histogram Binning without Sample Splitting
Chirag Gupta, Aaditya Ramdas
Poster
Wed 9:00 Two-way kernel matrix puncturing: towards resource-efficient PCA and spectral clustering
Romain COUILLET, Florent Chatelain, Nicolas Le Bihan
Poster
Wed 9:00 Functional Space Analysis of Local GAN Convergence
Valentin Khrulkov, Artem Babenko, Ivan Oseledets
Poster
Wed 9:00 On Energy-Based Models with Overparametrized Shallow Neural Networks
Carles Domingo-Enrich, Alberto Bietti, Eric Vanden-Eijnden, Joan Bruna
Poster
Wed 9:00 On the Implicit Bias of Initialization Shape: Beyond Infinitesimal Mirror Descent
Shahar Azulay, Edward Moroshko, Mor Shpigel Nacson, Blake Woodworth, Nati Srebro, Amir Globerson, Daniel Soudry
Poster
Wed 9:00 Agnostic Learning of Halfspaces with Gradient Descent via Soft Margins
Spencer Frei, Yuan Cao, Quanquan Gu
Poster
Wed 9:00 Provable Generalization of SGD-trained Neural Networks of Any Width in the Presence of Adversarial Label Noise
Spencer Frei, Yuan Cao, Quanquan Gu
Poster
Wed 9:00 Risk Bounds and Rademacher Complexity in Batch Reinforcement Learning
Yaqi Duan, Chi Jin, Zhiyuan Li
Poster
Wed 9:00 Towards Open Ad Hoc Teamwork Using Graph-based Policy Learning
Arrasy Rahman, Niklas Hopner, Filippos Christianos, Stefano V. Albrecht
Poster
Wed 9:00 The Hintons in your Neural Network: a Quantum Field Theory View of Deep Learning
Roberto Bondesan, Max Welling
Oral Session
Wed 17:00 Learning Theory 8
Oral Session
Wed 17:00 Reinforcement Learning Theory 2
Oral Session
Wed 17:00 Reinforcement Learning Theory 3
Oral Session
Wed 17:00 Learning Theory 7
Oral
Wed 17:00 The Implicit Bias for Adaptive Optimization Algorithms on Homogeneous Neural Networks
Bohan Wang, Qi Meng, Wei Chen, Tie-Yan Liu
Oral Session
Wed 17:00 Deep Learning Theory 4
Oral
Wed 17:00 Rate-Distortion Analysis of Minimum Excess Risk in Bayesian Learning
Hassan Hafez-Kolahi, Behrad Moniri, Shohreh Kasaei, Mahdieh Soleymani Baghshah
Spotlight
Wed 17:20 Asymmetric Heavy Tails and Implicit Bias in Gaussian Noise Injections
Alexander D Camuto, Xiaoyu Wang, Lingjiong Zhu, Christopher Holmes, Mert Gurbuzbalaban, Umut Simsekli
Spotlight
Wed 17:20 Near-Optimal Linear Regression under Distribution Shift
Qi Lei, Wei Hu, Jason Lee
Spotlight
Wed 17:25 Understanding Noise Injection in GANs
TaiGe Feng, Deli Zhao, Zheng-Jun Zha
Spotlight
Wed 17:25 Detection of Signal in the Spiked Rectangular Models
Ji Hyung Jung, Hye Won Chung, Ji Oon Lee
Spotlight
Wed 17:30 Near-Optimal Representation Learning for Linear Bandits and Linear RL
Jiachen Hu, Xiaoyu Chen, Chi Jin, Lihong Li, Liwei Wang
Spotlight
Wed 17:30 A Distribution-dependent Analysis of Meta Learning
Mikhail Konobeev, Ilja Kuzborskij, Csaba Szepesvari
Spotlight
Wed 17:30 FL-NTK: A Neural Tangent Kernel-based Framework for Federated Learning Analysis
Baihe Huang, Xiaoxiao Li, Zhao Song, Xin Yang
Spotlight
Wed 17:35 How Important is the Train-Validation Split in Meta-Learning?
Yu Bai, Minshuo Chen, Pan Zhou, Tuo Zhao, Jason Lee, Sham Kakade, Huan Wang, Caiming Xiong
Spotlight
Wed 17:35 Improved OOD Generalization via Adversarial Training and Pretraing
Mingyang Yi, Lu Hou, Jiacheng Sun, Lifeng Shang, Xin Jiang, Qun Liu, Zhiming Ma
Spotlight
Wed 17:35 Sparse Feature Selection Makes Batch Reinforcement Learning More Sample Efficient
Botao Hao, Yaqi Duan, Tor Lattimore, Csaba Szepesvari, Mengdi Wang
Spotlight
Wed 17:35 Improved Corruption Robust Algorithms for Episodic Reinforcement Learning
Yifang Chen, Simon Du, Kevin Jamieson
Spotlight
Wed 17:40 WGAN with an Infinitely Wide Generator Has No Spurious Stationary Points
Albert No, TaeHo Yoon, Sehyun Kwon, Ernest Ryu
Spotlight
Wed 17:40 Robust Unsupervised Learning via L-statistic Minimization
Andreas Maurer, Daniela Angela Parletta, Andrea Paudice, Massimiliano Pontil
Spotlight
Wed 17:45 A Theory of Label Propagation for Subpopulation Shift
Tianle Cai, Ruiqi Gao, Jason Lee, Qi Lei
Spotlight
Wed 17:45 Besov Function Approximation and Binary Classification on Low-Dimensional Manifolds Using Convolutional Residual Networks
Hao Liu, Minshuo Chen, Tuo Zhao, Wenjing Liao
Oral Session
Wed 18:00 Reinforcement Learning Theory 4
Oral
Wed 18:00 Dissecting Supervised Constrastive Learning
Florian Graf, Christoph Hofer, Marc Niethammer, Roland Kwitt
Oral Session
Wed 18:00 Learning Theory 11
Oral
Wed 18:00 Stability and Generalization of Stochastic Gradient Methods for Minimax Problems
Yunwen Lei, Zhenhuan Yang, Tianbao Yang, Yiming Ying
Oral Session
Wed 18:00 Deep Learning Theory 5
Oral Session
Wed 18:00 Learning Theory 10
Oral Session
Wed 18:00 Learning Theory 9
Spotlight
Wed 18:20 Noise and Fluctuation of Finite Learning Rate Stochastic Gradient Descent
Kangqiao Liu, Liu Ziyin, Masahito Ueda
Spotlight
Wed 18:20 Outside the Echo Chamber: Optimizing the Performative Risk
John Miller, Juan Perdomo, Tijana Zrnic
Spotlight
Wed 18:25 Tensor Programs IV: Feature Learning in Infinite-Width Neural Networks
Greg Yang, Edward Hu
Spotlight
Wed 18:25 Asymptotic Normality and Confidence Intervals for Prediction Risk of the Min-Norm Least Squares Estimator
Zeng Li, Chuanlong Xie, Qinwen Wang
Spotlight
Wed 18:30 Scaling Properties of Deep Residual Networks
Alain-Sam Cohen, Rama Cont, Alain Rossier, Renyuan Xu
Spotlight
Wed 18:30 Provable Meta-Learning of Linear Representations
Nilesh Tripuraneni, Chi Jin, Michael Jordan
Spotlight
Wed 18:35 Sample Complexity of Robust Linear Classification on Separated Data
Robi Bhattacharjee, Somesh Jha, Kamalika Chaudhuri
Spotlight
Wed 18:35 Contrastive Learning Inverts the Data Generating Process
Roland S. Zimmermann, Yash Sharma, Steffen Schneider, Matthias Bethge, Wieland Brendel
Spotlight
Wed 18:40 Tensor Programs IIb: Architectural Universality Of Neural Tangent Kernel Training Dynamics
Greg Yang, Etai Littwin
Spotlight
Wed 18:40 The Impact of Record Linkage on Learning from Feature Partitioned Data
Richard Nock, Stephen J Hardy, Wilko Henecka, Hamish Ivey-Law, Jakub Nabaglo, Giorgio Patrini, Guillaume Smith, Brian Thorne
Spotlight
Wed 18:45 Do We Actually Need Dense Over-Parameterization? In-Time Over-Parameterization in Sparse Training
Shiwei Liu, Lu Yin, Decebal Constantin Mocanu, Mykola Pechenizkiy
Spotlight
Wed 18:45 Train simultaneously, generalize better: Stability of gradient-based minimax learners
Farzan Farnia, Asuman Ozdaglar
Oral Session
Wed 19:00 Reinforcement Learning Theory 5
Oral Session
Wed 19:00 Learning Theory 12
Oral
Wed 19:00 Analysis of stochastic Lanczos quadrature for spectrum approximation
Tyler Chen, Thomas Trogdon, Shashanka Ubaru
Oral Session
Wed 19:00 Learning Theory 13
Oral
Wed 19:00 A Precise Performance Analysis of Support Vector Regression
Houssem Sifaou, Abla Kammoun, Mohamed-Slim Alouini
Spotlight
Wed 19:20 Sample-Optimal PAC Learning of Halfspaces with Malicious Noise
Jie Shen
Spotlight
Wed 19:20 Lower-Bounded Proper Losses for Weakly Supervised Classification
Shuhei M Yoshida, Takashi Takenouchi, Masashi Sugiyama
Spotlight
Wed 19:25 On Robust Mean Estimation under Coordinate-level Corruption
Zifan Liu, Jongho Park, Theo Rekatsinas, Christos Tzamos
Spotlight
Wed 19:25 On Variational Inference in Biclustering Models
Guanhua Fang, Ping Li
Spotlight
Wed 19:30 Infinite-Dimensional Optimization for Zero-Sum Games via Variational Transport
Lewis Liu, Yufeng Zhang, Zhuoran Yang, Reza Babanezhad, Zhaoran Wang
Spotlight
Wed 19:30 Multidimensional Scaling: Approximation and Complexity
Erik Demaine, Adam C Hesterberg, Frederic Koehler, Jayson Lynch, John C Urschel
Spotlight
Wed 19:35 Dropout: Explicit Forms and Capacity Control
Raman Arora, Peter Bartlett, Poorya Mianjy, Nati Srebro
Spotlight
Wed 19:35 Toward Better Generalization Bounds with Locally Elastic Stability
Zhun Deng, Hangfeng He, Weijie Su
Spotlight
Wed 19:40 Adaptive Newton Sketch: Linear-time Optimization with Quadratic Convergence and Effective Hessian Dimensionality
Jonathan Lacotte, Yifei Wang, Mert Pilanci
Spotlight
Wed 19:40 Finding Relevant Information via a Discrete Fourier Expansion
Mohsen Heidari, Jithin Sreedharan, Gil Shamir, Wojciech Szpankowski
Spotlight
Wed 19:45 Interpreting and Disentangling Feature Components of Various Complexity from DNNs
Jie Ren, Mingjie Li, Zexu Liu, Quanshi Zhang
Spotlight
Wed 19:45 On the Inherent Regularization Effects of Noise Injection During Training
Oussama Dhifallah, Yue Lu
Poster
Wed 21:00 Improved Corruption Robust Algorithms for Episodic Reinforcement Learning
Yifang Chen, Simon Du, Kevin Jamieson
Poster
Wed 21:00 Outside the Echo Chamber: Optimizing the Performative Risk
John Miller, Juan Perdomo, Tijana Zrnic
Poster
Wed 21:00 Tensor Programs IIb: Architectural Universality Of Neural Tangent Kernel Training Dynamics
Greg Yang, Etai Littwin
Poster
Wed 21:00 Lower-Bounded Proper Losses for Weakly Supervised Classification
Shuhei M Yoshida, Takashi Takenouchi, Masashi Sugiyama
Poster
Wed 21:00 Do We Actually Need Dense Over-Parameterization? In-Time Over-Parameterization in Sparse Training
Shiwei Liu, Lu Yin, Decebal Constantin Mocanu, Mykola Pechenizkiy
Poster
Wed 21:00 Toward Better Generalization Bounds with Locally Elastic Stability
Zhun Deng, Hangfeng He, Weijie Su
Poster
Wed 21:00 Besov Function Approximation and Binary Classification on Low-Dimensional Manifolds Using Convolutional Residual Networks
Hao Liu, Minshuo Chen, Tuo Zhao, Wenjing Liao
Poster
Wed 21:00 Detection of Signal in the Spiked Rectangular Models
Ji Hyung Jung, Hye Won Chung, Ji Oon Lee
Poster
Wed 21:00 Improved OOD Generalization via Adversarial Training and Pretraing
Mingyang Yi, Lu Hou, Jiacheng Sun, Lifeng Shang, Xin Jiang, Qun Liu, Zhiming Ma
Poster
Wed 21:00 Asymptotic Normality and Confidence Intervals for Prediction Risk of the Min-Norm Least Squares Estimator
Zeng Li, Chuanlong Xie, Qinwen Wang
Poster
Wed 21:00 Train simultaneously, generalize better: Stability of gradient-based minimax learners
Farzan Farnia, Asuman Ozdaglar
Poster
Wed 21:00 On Variational Inference in Biclustering Models
Guanhua Fang, Ping Li
Poster
Wed 21:00 FL-NTK: A Neural Tangent Kernel-based Framework for Federated Learning Analysis
Baihe Huang, Xiaoxiao Li, Zhao Song, Xin Yang
Poster
Wed 21:00 Contrastive Learning Inverts the Data Generating Process
Roland S. Zimmermann, Yash Sharma, Steffen Schneider, Matthias Bethge, Wieland Brendel
Poster
Wed 21:00 The Impact of Record Linkage on Learning from Feature Partitioned Data
Richard Nock, Stephen J Hardy, Wilko Henecka, Hamish Ivey-Law, Jakub Nabaglo, Giorgio Patrini, Guillaume Smith, Brian Thorne
Poster
Wed 21:00 Sparse Feature Selection Makes Batch Reinforcement Learning More Sample Efficient
Botao Hao, Yaqi Duan, Tor Lattimore, Csaba Szepesvari, Mengdi Wang
Poster
Wed 21:00 Noise and Fluctuation of Finite Learning Rate Stochastic Gradient Descent
Kangqiao Liu, Liu Ziyin, Masahito Ueda
Poster
Wed 21:00 Sample-Optimal PAC Learning of Halfspaces with Malicious Noise
Jie Shen
Poster
Wed 21:00 Tensor Programs IV: Feature Learning in Infinite-Width Neural Networks
Greg Yang, Edward Hu
Poster
Wed 21:00 Adaptive Newton Sketch: Linear-time Optimization with Quadratic Convergence and Effective Hessian Dimensionality
Jonathan Lacotte, Yifei Wang, Mert Pilanci
Poster
Wed 21:00 The Implicit Bias for Adaptive Optimization Algorithms on Homogeneous Neural Networks
Bohan Wang, Qi Meng, Wei Chen, Tie-Yan Liu
Poster
Wed 21:00 A Distribution-dependent Analysis of Meta Learning
Mikhail Konobeev, Ilja Kuzborskij, Csaba Szepesvari
Poster
Wed 21:00 Interpreting and Disentangling Feature Components of Various Complexity from DNNs
Jie Ren, Mingjie Li, Zexu Liu, Quanshi Zhang
Poster
Wed 21:00 WGAN with an Infinitely Wide Generator Has No Spurious Stationary Points
Albert No, TaeHo Yoon, Sehyun Kwon, Ernest Ryu
Poster
Wed 21:00 A Theory of Label Propagation for Subpopulation Shift
Tianle Cai, Ruiqi Gao, Jason Lee, Qi Lei
Poster
Wed 21:00 On the Inherent Regularization Effects of Noise Injection During Training
Oussama Dhifallah, Yue Lu
Poster
Wed 21:00 Scaling Properties of Deep Residual Networks
Alain-Sam Cohen, Rama Cont, Alain Rossier, Renyuan Xu
Poster
Wed 21:00 Stability and Generalization of Stochastic Gradient Methods for Minimax Problems
Yunwen Lei, Zhenhuan Yang, Tianbao Yang, Yiming Ying
Poster
Wed 21:00 Understanding Noise Injection in GANs
TaiGe Feng, Deli Zhao, Zheng-Jun Zha
Poster
Wed 21:00 Multidimensional Scaling: Approximation and Complexity
Erik Demaine, Adam C Hesterberg, Frederic Koehler, Jayson Lynch, John C Urschel
Poster
Wed 21:00 A Precise Performance Analysis of Support Vector Regression
Houssem Sifaou, Abla Kammoun, Mohamed-Slim Alouini
Poster
Wed 21:00 Near-Optimal Linear Regression under Distribution Shift
Qi Lei, Wei Hu, Jason Lee
Poster
Wed 21:00 Sample Complexity of Robust Linear Classification on Separated Data
Robi Bhattacharjee, Somesh Jha, Kamalika Chaudhuri
Poster
Wed 21:00 Analysis of stochastic Lanczos quadrature for spectrum approximation
Tyler Chen, Thomas Trogdon, Shashanka Ubaru
Poster
Wed 21:00 Provable Meta-Learning of Linear Representations
Nilesh Tripuraneni, Chi Jin, Michael Jordan
Poster
Wed 21:00 On Robust Mean Estimation under Coordinate-level Corruption
Zifan Liu, Jongho Park, Theo Rekatsinas, Christos Tzamos
Poster
Wed 21:00 Infinite-Dimensional Optimization for Zero-Sum Games via Variational Transport
Lewis Liu, Yufeng Zhang, Zhuoran Yang, Reza Babanezhad, Zhaoran Wang
Poster
Wed 21:00 Robust Unsupervised Learning via L-statistic Minimization
Andreas Maurer, Daniela Angela Parletta, Andrea Paudice, Massimiliano Pontil
Poster
Wed 21:00 Near-Optimal Representation Learning for Linear Bandits and Linear RL
Jiachen Hu, Xiaoyu Chen, Chi Jin, Lihong Li, Liwei Wang
Poster
Wed 21:00 Dropout: Explicit Forms and Capacity Control
Raman Arora, Peter Bartlett, Poorya Mianjy, Nati Srebro
Poster
Wed 21:00 How Important is the Train-Validation Split in Meta-Learning?
Yu Bai, Minshuo Chen, Pan Zhou, Tuo Zhao, Jason Lee, Sham Kakade, Huan Wang, Caiming Xiong
Poster
Wed 21:00 Asymmetric Heavy Tails and Implicit Bias in Gaussian Noise Injections
Alexander D Camuto, Xiaoyu Wang, Lingjiong Zhu, Christopher Holmes, Mert Gurbuzbalaban, Umut Simsekli
Poster
Wed 21:00 Dissecting Supervised Constrastive Learning
Florian Graf, Christoph Hofer, Marc Niethammer, Roland Kwitt
Poster
Wed 21:00 Finding Relevant Information via a Discrete Fourier Expansion
Mohsen Heidari, Jithin Sreedharan, Gil Shamir, Wojciech Szpankowski
Poster
Wed 21:00 Rate-Distortion Analysis of Minimum Excess Risk in Bayesian Learning
Hassan Hafez-Kolahi, Behrad Moniri, Shohreh Kasaei, Mahdieh Soleymani Baghshah
Oral
Thu 5:00 Local Algorithms for Finding Densely Connected Clusters
Peter Macgregor, He Sun
Oral Session
Thu 5:00 Deep Learning Theory 6
Oral
Thu 5:00 Tilting the playing field: Dynamical loss functions for machine learning
Miguel Ruiz Garcia, Ge Zhang, Samuel Schoenholz, Andrea Liu
Spotlight
Thu 5:20 Adversarial Robustness Guarantees for Random Deep Neural Networks
Giacomo De Palma, Bobak T Kiani, Seth Lloyd
Spotlight
Thu 5:25 Implicit Bias of Linear RNNs
Melika Emami, Moji Sahraee-Ardakan, Parthe Pandit, Sundeep Rangan, Alyson Fletcher
Spotlight
Thu 5:30 Analyzing the tree-layer structure of Deep Forests
Ludovic Arnould, Claire Boyer, Erwan Scornet
Spotlight
Thu 5:35 Quantifying the Benefit of Using Differentiable Learning over Tangent Kernels
Eran Malach, Pritish Kamath, Emmanuel Abbe, Nati Srebro
Spotlight
Thu 5:40 Implicit Regularization in Tensor Factorization
Noam Razin, Asaf Maman, Nadav Cohen
Spotlight
Thu 5:45 Uniform Convergence, Adversarial Spheres and a Simple Remedy
Gregor Bachmann, Seyed Moosavi, Thomas Hofmann
Oral Session
Thu 6:00 Learning Theory 14
Oral
Thu 6:00 Improved, Deterministic Smoothing for L_1 Certified Robustness
Alexander Levine, Soheil Feizi
Spotlight
Thu 6:45 Learning Interaction Kernels for Agent Systems on Riemannian Manifolds
Mauro Maggioni, Jason Miller, Hongda Qiu, Ming Zhong
Poster
Thu 9:00 Implicit Regularization in Tensor Factorization
Noam Razin, Asaf Maman, Nadav Cohen
Poster
Thu 9:00 Learning Interaction Kernels for Agent Systems on Riemannian Manifolds
Mauro Maggioni, Jason Miller, Hongda Qiu, Ming Zhong
Poster
Thu 9:00 Uniform Convergence, Adversarial Spheres and a Simple Remedy
Gregor Bachmann, Seyed Moosavi, Thomas Hofmann
Poster
Thu 9:00 Implicit Bias of Linear RNNs
Melika Emami, Moji Sahraee-Ardakan, Parthe Pandit, Sundeep Rangan, Alyson Fletcher
Poster
Thu 9:00 Analyzing the tree-layer structure of Deep Forests
Ludovic Arnould, Claire Boyer, Erwan Scornet
Poster
Thu 9:00 Local Algorithms for Finding Densely Connected Clusters
Peter Macgregor, He Sun
Poster
Thu 9:00 Quantifying the Benefit of Using Differentiable Learning over Tangent Kernels
Eran Malach, Pritish Kamath, Emmanuel Abbe, Nati Srebro
Poster
Thu 9:00 Adversarial Robustness Guarantees for Random Deep Neural Networks
Giacomo De Palma, Bobak T Kiani, Seth Lloyd
Poster
Thu 9:00 Tilting the playing field: Dynamical loss functions for machine learning
Miguel Ruiz Garcia, Ge Zhang, Samuel Schoenholz, Andrea Liu
Poster
Thu 9:00 Improved, Deterministic Smoothing for L_1 Certified Robustness
Alexander Levine, Soheil Feizi
Spotlight
Thu 17:25 REPAINT: Knowledge Transfer in Deep Reinforcement Learning
Yunzhe Tao, Sahika Genc, Jonathan Chung, TAO SUN, Sunil Mallya
Spotlight
Thu 18:30 Efficient Online Learning for Dynamic k-Clustering
Dimitris Fotakis, Georgios Piliouras, Stratis Skoulakis
Spotlight
Thu 18:45 Which transformer architecture fits my data? A vocabulary bottleneck in self-attention
Noam Wies, Yoav Levine, Daniel Jannai, Amnon Shashua
Spotlight
Thu 19:35 GBHT: Gradient Boosting Histogram Transform for Density Estimation
Jingyi Cui, Hanyuan Hang, Yisen Wang, Zhouchen Lin
Spotlight
Thu 20:30 Discretization Drift in Two-Player Games
Mihaela Rosca, Yan Wu, Benoit Dherin, David GT Barrett
Spotlight
Thu 20:35 Elementary superexpressive activations
Dmitry Yarotsky
Spotlight
Thu 20:35 Boosting for Online Convex Optimization
Elad Hazan, Karan Singh
Spotlight
Thu 20:40 Online Learning with Optimism and Delay
Genevieve Flaspohler, Francesco Orabona, Judah Cohen, Soukayna Mouatadid, Miruna Oprescu, Paulo Orenstein, Lester Mackey
Spotlight
Thu 20:45 Learner-Private Convex Optimization
Jiaming Xu, Kuang Xu, Dana Yang
Spotlight
Thu 20:45 Smooth $p$-Wasserstein Distance: Structure, Empirical Approximation, and Statistical Applications
Sloan Nietert, Ziv Goldfeld, Kengo Kato
Spotlight
Thu 20:50 How rotational invariance of common kernels prevents generalization in high dimensions
Konstantin Donhauser, Mingqi Wu, Fanny Yang
Poster
Thu 21:00 How rotational invariance of common kernels prevents generalization in high dimensions
Konstantin Donhauser, Mingqi Wu, Fanny Yang
Poster
Thu 21:00 Smooth $p$-Wasserstein Distance: Structure, Empirical Approximation, and Statistical Applications
Sloan Nietert, Ziv Goldfeld, Kengo Kato
Poster
Thu 21:00 Online Learning with Optimism and Delay
Genevieve Flaspohler, Francesco Orabona, Judah Cohen, Soukayna Mouatadid, Miruna Oprescu, Paulo Orenstein, Lester Mackey
Poster
Thu 21:00 REPAINT: Knowledge Transfer in Deep Reinforcement Learning
Yunzhe Tao, Sahika Genc, Jonathan Chung, TAO SUN, Sunil Mallya
Poster
Thu 21:00 Elementary superexpressive activations
Dmitry Yarotsky
Poster
Thu 21:00 Discretization Drift in Two-Player Games
Mihaela Rosca, Yan Wu, Benoit Dherin, David GT Barrett
Poster
Thu 21:00 Efficient Online Learning for Dynamic k-Clustering
Dimitris Fotakis, Georgios Piliouras, Stratis Skoulakis
Poster
Thu 21:00 Which transformer architecture fits my data? A vocabulary bottleneck in self-attention
Noam Wies, Yoav Levine, Daniel Jannai, Amnon Shashua
Poster
Thu 21:00 GBHT: Gradient Boosting Histogram Transform for Density Estimation
Jingyi Cui, Hanyuan Hang, Yisen Wang, Zhouchen Lin
Poster
Thu 21:00 Boosting for Online Convex Optimization
Elad Hazan, Karan Singh
Poster
Thu 21:00 Learner-Private Convex Optimization
Jiaming Xu, Kuang Xu, Dana Yang
Workshop
Sat 7:00 Information-Theoretic Methods for Rigorous, Responsible, and Reliable Machine Learning (ITR3)
Ahmad Beirami, Flavio Calmon, Berivan Isik, Haewon Jeong, Matthew Nokleby, Cynthia Rush
Workshop
Sat 9:00 Workshop on Reinforcement Learning Theory
Shipra Agrawal, Simon Du, Niao He, Csaba Szepesvari, Lin Yang
Workshop
Sat 12:04 Unconstrained Submodular Maximization with Modular Costs: Tight Approximation and Application to Profit Maximization
Tianyuan Jin, Yu Yang, Renchi Yang, Jieming Shi, Keke Huang, Xiaokui Xiao
Workshop
Sat 15:40 An Extreme Point Approach to Subset Selection
Viveck Cadambe, Bill Kay
Workshop
MetaDataset: A Dataset of Datasets for Evaluating Distribution Shifts and Training Conflicts
Weixin Liang, James Zou, Weixin Liang
Workshop
Characterizing the Generalization Error of Gibbs Algorithm with Symmetrized KL information
Gholamali Aminian, Yuheng Bu, Laura Toni, Miguel Rodrigues, Gregory Wornell
Workshop
Robust Generalization of Quadratic Neural Networks via Function Identification
Kan Xu, Hamsa Bastani, Osbert Bastani
Workshop
On the interplay between data structure and loss function: an analytical study of generalization for classification
Stéphane d'Ascoli, Marylou Gabrié, Levent Sagun, Giulio Biroli
Workshop
Strategic Instrumental Variable Regression: Recovering Causal Relationships From Strategic Responses
Keegan Harris, Daniel Ngo, Logan Stapleton, Hoda Heidari, Steven Wu
Workshop
Adversarial Sample Detection via Channel Pruning
Zuohui Chen, RenXuan Wang, Yao Lu, jingyang Xiang, Qi Xuan
Workshop
Unconstrained Submodular Maximization with Modular Costs: Tight Approximation and Application to Profit Maximization
Tianyuan Jin, Yu Yang, Renchi Yang, Jieming Shi, Keke Huang, Xiaokui Xiao
Workshop
Improve Generalization and Robustness of Neural Networks via Weight Scale Shifting Invariant Regularizations
Ziquan Liu, Yufei Cui, Antoni Chan
Workshop
An Extreme Point Approach to Subset Selection
Viveck Cadambe, Bill Kay