Sébastien Bubeck

How to Fine-Tune Vision Models with SGD ICLR 2024 On the complexity of finding stationary points of smooth functions in one dimension ALT 2023 Learning threshold neurons via edge of stability NIPS 2023 AutoMoE: Heterogeneous Mixture-of-Experts with Adaptive Computation for Efficient Neural Machine Translation ACL 2023 Data Augmentation as Feature Manipulation ICML 2022 LiteTransformerSearch: Training-free Neural Architecture Search for Efficient Language Models NIPS 2022 Adversarial Examples in Multi-Layer Random ReLU Networks NIPS 2021 A Universal Law of Robustness via Isoperimetry NIPS 2021 A Law of Robustness for Two-Layers Neural Networks COLT 2021 Cooperative and Stochastic Multi-Player Multi-Armed Bandit: Optimal Regret With Neither Communication Nor Collisions COLT 2021 A single gradient step finds adversarial examples on random two-layers neural networks NIPS 2021 First-Order Bayesian Regret Analysis of Thompson Sampling ALT 2020 Statistically Preconditioned Accelerated Gradient Method for Distributed Optimization ICML 2020 Coordination without communication: optimal regret in two players multi-armed bandits COLT 2020 How to Trap a Gradient Flow COLT 2020 Online Learning for Active Cache Synchronization ICML 2020 Network size and size of the weights in memorization with two-layers neural networks NIPS 2020 Non-Stochastic Multi-Player Multi-Armed Bandits: Optimal Rate With Collision Information, Sublinear Without COLT 2020 Improved Path-length Regret Bounds for Bandits COLT 2019 Optimal Convergence Rates for Convex Distributed Optimization in Networks JMLR 2019 Multi-scale Online Learning: Theory and Applications to Online Auctions and Pricing JMLR 2019 Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers NIPS 2019 Complexity of Highly Parallel Non-Smooth Convex Optimization NIPS 2019 Adversarial examples from computational constraints ICML 2019 Near-optimal method for highly smooth convex optimization COLT 2019 Near Optimal Methods for Minimizing Convex Functions with Lipschitz $p$-th Derivatives COLT 2019 Is Q-Learning Provably Efficient? NIPS 2018 Optimal Algorithms for Non-Smooth Distributed Optimization in Networks NIPS 2018 Conference on Learning Theory 2018: Preface COLT 2018 Make the Minority Great Again: First-Order Regret Bound for Contextual Bandits ICML 2018 Sparsity, variance and curvature in multi-armed bandits ALT 2018 Optimal Algorithms for Smooth and Strongly Convex Distributed Optimization in Networks ICML 2017 Multi-scale exploration of convex functions and bandit convex optimization COLT 2016 Black-box Optimization with a Politician ICML 2016 Finite-Time Analysis of Projected Langevin Monte Carlo NIPS 2015 Bandit Convex Optimization: \sqrtT Regret in One Dimension COLT 2015 The entropic barrier: a simple and optimal universal self-concordant barrier COLT 2015 Exceptional Rotations of Random Graphs: A VC Theory JMLR 2015 lil’ UCB : An Optimal Exploration Algorithm for Multi-Armed Bandits COLT 2014 Most Correlated Arms Identification COLT 2014 Prior-free and prior-dependent regret bounds for Thompson Sampling NIPS 2013 Bounded regret in stochastic multi-armed bandits COLT 2013 Optimal Discovery with Probabilistic Expert Advice: Finite Time Analysis and Macroscopic Optimality JMLR 2013 The Best of Both Worlds: Stochastic and Adversarial Bandits COLT 2012 Towards Minimax Policies for Online Linear Optimization with Bandit Feedback COLT 2012 Minimax Policies for Combinatorial Prediction Games COLT 2011 -Armed Bandits JMLR 2011 Multi-Bandit Best Arm Identification NIPS 2011 Regret Bounds and Minimax Policies under Partial Monitoring JMLR 2010 Nearest Neighbor Clustering: A Baseline Method for Consistent Clustering with Arbitrary Objective Functions JMLR 2009 Online Optimization in X-Armed Bandits NIPS 2008 Consistent Minimization of Clustering Objective Functions NIPS 2007