Proceedings
https://proceedings.mlr.press/v201/
Best Paper Award
On Computable Online Learning
Niki Hasrati (University of Waterloo), Shai Ben-David (University of Waterloo)
Best Student Paper Award
On the complexity of finding stationary points of smooth functions in one dimension
Sinho Chewi (Massachusetts Institute of Technology), Sebastien Bubeck (Microsoft Research), Adil Salim (Microsoft Research)
Accepted Papers
- Tournaments, Johnson Graphs and NC-Teaching
Hans U. Simon (Ruhr University Bochum) - Spatially Adaptive Online Prediction of Piecewise Regular Functions
Sabyasachi Chatterjee (University of Illinois Urbana-Champaign), Subhajit Goswami (Tata Institute of Fundamental Research, Bombay) - On the complexity of finding stationary points of smooth functions in one dimension
Sinho Chewi (Massachusetts Institute of Technology), Sebastien Bubeck (Microsoft Research), Adil Salim (Microsoft Research) - Private Stochastic Optimization with Large Worst-Case Lipschitz Parameter: Optimal Rates for (Non-Smooth) Convex Losses and Extension to Non-Convex Losses
Andrew Lowy (USC), Meisam Razaviyayn (USC) - Convergence of score-based generative modeling for general data distributions
Holden Lee (Johns Hopkins University), Jianfeng Lu (Duke University), Yixin Tan (Duke University) - Towards Empirical Process Theory for Vector-Valued Functions: Metric Entropy of Smooth Function Classes
Junhyung Park (MPI for Intelligent Systems, Tübingen), Krikamol Muandet (CISPA) - Implicit Regularization Towards Rank Minimization in ReLU Networks
Nadav Timor (Weizmann Institute of Science), Gal Vardi (TTIC), Ohad Shamir (Weizmann Institute of Science) - On Best-Arm Identification with a Fixed Budget in Non-Parametric Multi-Armed Bandits
Antoine Barrier (École Normale Supérieure de Lyon & Université Paris-Saclay), Aurélien Garivier (ENS Lyon), Gilles Stoltz (CNRS / Université Paris Saclay / HEC Paris) - Variance-Reduced Conservative Policy Iteration
Naman Agarwal (Google), Brian Bullins (Purdue University), Karan Singh (Carnegie Mellon University) - Reconstructing Ultrametric Trees from Noisy Experiments
Eshwar Ram Arunachaleswaran (University of Pennsylvania), Sampath Kannan (University of Pennsylvania), Anindya De (-) - Dealing with Unknown Variances in Best-Arm Identification
Marc Jourdan (Universite de Lille), Rémy Degenne (Inria), Emilie Kaufmann (CNRS) - Constant regret for sequence prediction with limited advice
El Mehdi Saad (Paris Saclay University), Gilles Blanchard (Paris Saclay University) - Follow-the-Perturbed-Leader Achieves Best-of-Both-Worlds for Bandit Problems
Junya Honda (Kyoto University / RIKEN), Shinji Ito (NEC Corporation), Taira Tsuchiya (Kyoto University / RIKEN) - Algorithmic Stability of Heavy-Tailed Stochastic Gradient Descent on Least Squares
Anant Raj (SIERRA, Inria), Melih Barsbey (Boğaziçi University), Mert Gurbuzbalaban (Rutgers), Lingjiong Zhu (FSU), Umut Simsekli (Inria/ENS) - SQ Lower Bounds for Random Sparse Planted Vector Problem
Yiding Hua (ETH Zürich), Jingqiu Ding (ETH Zurich) - On The Computational Complexity of Self-Attention
Feyza Duman Keles (NYU), Maheshakya Wijewardena (University of Utah), Chinmay Hegde (New York University) - Linear Reinforcement Learning with Ball Structure Action Space
Zeyu Jia (MIT), Randy Jia (Amazon), Dhruv Madeka (Amazon), Dean Foster (Amazon) - Max-Quantile Grouped Infinite-Arm Bandits
Ivan Lau (Rice University), Yan Hao Ling (National University of Singapore), Mayank Shrivastava (UIUC), Jonathan Scarlett (National University of Singapore) - Best-of-Both-Worlds Algorithms for Partial Monitoring
Taira Tsuchiya (Kyoto University / RIKEN), Shinji Ito (NEC Corporation), Junya Honda (Kyoto University / RIKEN) - Wide stochastic networks: Gaussian limit and PAC-Bayesian training
Eugenio Clerico (University of Oxford), George Deligiannidis (Oxford), Arnaud Doucet (Oxford University) - Reaching Goals is Hard: Settling the Sample Complexity of the Stochastic Shortest Path
Liyu Chen (USC), Andrea Tirinzoni (Meta AI), Matteo Pirotta (META), Alessandro Lazaric (Facebook) - Online Learning with Off-Policy Feedback
Germano Gabbianelli (Universitat Pompeu Fabra), Gergely Neu (Universitat Pompeu Fabra), Matteo Papini (Universitat Pompeu Fabra) - Perceptronic Complexity and Online Matrix Completion
Stephen U Pasteris (University College London) - Efficient Global Planning in Large MDPs via Stochastic Primal-Dual Optimization
Gergely Neu (Universitat Pompeu Fabra), Nneka M Okolo (Pompeu Fabra University) - Spectral Subspace Dictionary Learning
Stephen E White (Penn State University), Alexei Novikov (Penn State University) - Projection-free Adaptive Regret with Membership Oracles
Zhou Lu (Princeton University), Nataly Brukhim (Princeton University), Paula Gradu (UC Berkeley), Elad Hazan (Princeton University) - Limitations of Information-Theoretic Generalization Bounds for Gradient Descent Methods in Stochastic Convex Optimization
Mahdi Haghifam (University of Toronto), Borja Rodríguez Gálvez (KTH Royal Institute of Technology), Ragnar Thobaben (KTH Royal Institute of Technology), Mikael Skoglund (KTH Royal Institute of Technology), Daniel M. Roy (University of Toronto), Gintare Karolina Dziugaite (Google Research) - A Query Algorithm for Learning a Spanning Forest in Weighted Undirected Graphs
Hang Liao (Dartmouth College), Deeparnab Chakrabarty (Dartmouth College) - The Replicator Dynamic, Chain Components and the Response Graph
Oliver Biggar (Australian National University), Iman Shames (The Australian National University) - Improved High-Probability Regret for Adversarial Bandits with Time-Varying Feedback Graphs
Haipeng Luo (USC), Hanghang Tong (University of Illinois at Urbana-Champaign), Mengxiao Zhang (University of Southern California), Yuheng Zhang (University of Illinois at Urbana-Champaign) - Universal Bias Reduction in Estimation of Smooth Additive Function in High Dimensions
Fan Zhou (Georgia Institute of Technology), Ping Li (Baidu), Cun-Hui Zhang (Rutgers University) - Fisher information lower bounds for sampling
Sinho Chewi (Massachusetts Institute of Technology), Patrik R Gerber (MIT), Holden Lee (Johns Hopkins University), Chen Lu (Massachusetts Institute of Technology) - Adversarially Robust Learning with Tolerance
Hassan Ashtiani (McMaster University), Vinayak Pathak (Layer6 AI), Ruth Urner (York University) - Optimistic PAC Reinforcement Learning: the Instance-Dependent View
Andrea Tirinzoni (Meta AI), Aymen Al Marjani (ENS Lyon), Emilie Kaufmann (CNRS) - Robust Estimation of Discrete Distributions under Local Differential Privacy
Julien CHHOR (CREST/ENSAE), Flore Sentenac (ENSAE) - Adversarial Online Multi-Task Reinforcement Learning
Quan M Nguyen (University of Victoria), Nishant Mehta (University of Victoria) - Pseudonorm Approachability and Applications to Regret Minimization
Chris Dann (Google), Yishay Mansour (Google and Tel Aviv University), Mehryar Mohri (Google Research & Courant Institute of Mathematical Sciences, NYU), Jon Schneider (Google), Balasubramanian Sivan (Google Research) - Robust Empirical Risk Minimization with Tolerance
Robi Bhattacharjee (University of California, San Diego), Max Hopkins (University of California San Diego), Akash Kumar (University of California San Diego), Hantao Yu (Columbia University), Kamalika Chaudhuri (University of California, San Diego) - Online k-means Clustering on Arbitrary Data Streams
Robi Bhattacharjee (University of California, San Diego), Jacob J Imola (UCSD), Michal Moshkovitz (TAU), Sanjoy Dasgupta (UCSD) - Online Self-Concordant and Relatively Smooth Minimization, With Applications to Online Portfolio Selection and Learning Quantum States
Chung-En Tsai (National Taiwan University), Hao-Chung Cheng (National Taiwan University), Yen-Huan Li (National Taiwan University) - Testing Tail Weight of a Distribution Via Hazard Rate
Maryam Aliakbarpour (MIT), Amartya Biswas (MIT), Kavya Ravichandran (Toyota Technological Institute at Chicago), Ronitt Rubinfeld (MIT, TAU) - An Instance-Dependent Analysis for the Cooperative Multi-Player Multi-Armed Bandit
Aldo Pacchiano (Microsoft, Immunai), Peter Bartlett (), Michael Jordan (UC Berkeley) - On Computable Online Learning
Niki Hasrati (University of Waterloo), Shai Ben-David (University of Waterloo) - A Unified Algorithm for Stochastic Path Problems
Chris Dann (Google), Chen-Yu Wei (University of Southern California), Julian Zimmert (Google) - Online Learning for Traffic Navigation in Congested Networks
Sreenivas Gollapudi (Google Research), Kostas Kollias (Google Research), Chinmay Maheshwari (University of California Berkeley), Manxi Wu (Cornell University ) - Complexity Analysis of a Countable-armed Bandit Problem
Anand Kalvit (Columbia University), Assaf Zeevi (Columbia University) - Adaptive Power Method: Eigenvector Estimation from Sampled Data
Seiyun Shin (University of Illinois at Urbana-Champaign), Han Zhao (University of Illinois at Urbana-Champaign), Ilan Shomorony (University of Illinois at Urbana Champaign) - Primal-Dual Algorithms with Predictions for Online Bounded Allocation and Ad-Auctions Problems
Kim Thang Nguyen (LIG, University Grenoble-Alpes), Enikő Kevi (UGA)