Tomer Koren

Complexity of Vector-valued Prediction: From Linear Models to Stochastic Convex Optimization ALT 2026 From Continual Learning to SGD and Back: Better Rates for Continual Linear Models ALT 2026 Statistical Learning from Attribution Sets COLT 2026 The Hidden Cost of Approximation in Online Mirror Descent COLT 2026 The Sample Complexity of Multiclass and Sparse Contextual Bandits COLT 2026 Convergence of Policy Mirror Descent Beyond Compatible Function Approximation ICML 2025 Dueling Convex Optimization with General Preferences ICML 2025 Faster Stochastic Optimization with Arbitrary Delays via Adaptive Asynchronous Mini-Batching ICML 2025 Locally Optimal Descent for Dynamic Stepsize Scheduling AISTATS 2025 Nearly Optimal Sample Complexity for Learning with Label Proportions ICML 2025 Rapid Overfitting of Multi-Pass SGD in Stochastic Convex Optimization ICML 2025 The Dimension Strikes Back with Gradients: Generalization of Gradient Methods in Stochastic Convex Optimization ALT 2025 Faster Convergence with MultiWay Preferences AISTATS 2024 Fast Rates for Bandit PAC Multiclass Classification NeurIPS 2024 How Free is Parameter-Free Stochastic Optimization? ICML 2024 Private Online Learning via Lazy Algorithms NeurIPS 2024 Rate-Optimal Policy Optimization for Linear Markov Decision Processes ICML 2024 The Real Price of Bandit Information in Multiclass Classification COLT 2024 Improved Regret for Efficient Online Reinforcement Learning with Linear Function Approximation ICML 2023 Near-Optimal Algorithms for Private Online Optimization in the Realizable Regime ICML 2023 Private Online Prediction from Experts: Separations and Faster Rates COLT 2023 Regret Minimization and Convergence to Equilibria in General-sum Markov Games ICML 2023 SGD with AdaGrad Stepsizes: Full Adaptivity with High Probability to Unknown Parameters, Unbounded Gradients and Affine Variance ICML 2023 Tight Risk Bounds for Gradient Descent on Separable Data NeurIPS 2023 Benign Underfitting of Stochastic Gradient Descent NeurIPS 2022 Better Best of Both Worlds Bounds for Bandits with Switching Costs NeurIPS 2022 Efficient Online Linear Control with Stochastic Convex Costs and Unknown Dynamics COLT 2022 Rate-Optimal Online Convex Optimization in Adaptive Linear Control NeurIPS 2022 Stability vs Implicit Bias of Gradient Methods on Separable Data and Beyond COLT 2022 Uniform Stability for First-Order Empirical Risk Minimization COLT 2022 Adversarial Dueling Bandits ICML 2021 Algorithmic Instabilities of Accelerated Gradient Descent NeurIPS 2021 Asynchronous Stochastic Optimization Robust to Arbitrary Delays NeurIPS 2021 Dueling Convex Optimization ICML 2021 Lazy OCO: Online Convex Optimization on a Switching Budget COLT 2021 Never Go Full Batch (in Stochastic Convex Optimization) NeurIPS 2021 Online Markov Decision Processes with Aggregate Bandit Feedback COLT 2021 Online Policy Gradient for Model Free Learning of Linear Quadratic Regulators with $\sqrt$T Regret ICML 2021 Optimal Rates for Random Order Online Optimization NeurIPS 2021 Private Stochastic Convex Optimization: Optimal Rates in L1 Geometry ICML 2021 SGD Generalizes Better Than GD (And Regularization Doesn’t Help) COLT 2021 Stochastic Multi-Armed Bandits with Unrestricted Delay Distributions ICML 2021 Towards Best-of-All-Worlds Online Learning with Feedback Graphs NeurIPS 2021 Bandit Linear Control NeurIPS 2020 Can Implicit Bias Explain Generalization? Stochastic Convex Optimization as a Case Study NeurIPS 2020 Logarithmic Regret for Learning Linear Quadratic Regulators Efficiently ICML 2020 Open Problem: Tight Convergence of SGD in Constant Dimension COLT 2020 Prediction with Corrupted Expert Advice NeurIPS 2020 Stochastic Optimization with Laggard Data Pipelines NeurIPS 2020 Better Algorithms for Stochastic Bandits with Adversarial Corruptions COLT 2019 Learning Linear-Quadratic Regulators Efficiently with only √T Regret ICML 2019 Memory Efficient Adaptive Optimization NeurIPS 2019 Robust Bi-Tempered Logistic Loss Based on Bregman Divergences NeurIPS 2019 Semi-Cyclic Stochastic Gradient Descent ICML 2019 Online Linear Quadratic Control ICML 2018 Shampoo: Preconditioned Stochastic Tensor Optimization ICML 2018 Affine-Invariant Online Optimization and the Low-rank Experts Problem NeurIPS 2017 Bandits with Movement Costs and Adaptive Pricing COLT 2017 Multi-Armed Bandits with Metric Movement Costs NeurIPS 2017 Tight Bounds for Bandit Combinatorial Optimization COLT 2017 Online Learning with Feedback Graphs Without the Graphs ICML 2016 Online Learning with Low Rank Experts COLT 2016 Online Pricing with Strategic and Patient Buyers NeurIPS 2016 The Limits of Learning with Missing Data NeurIPS 2016 Bandit Convex Optimization: \sqrtT Regret in One Dimension COLT 2015 Bandit Smooth Convex Optimization: Improving the Bias-Variance Tradeoff NeurIPS 2015 Fast Rates for Exp-concave Empirical Risk Minimization NeurIPS 2015 Online Learning with Feedback Graphs: Beyond Bandits COLT 2015 Logistic Regression: Tight Bounds for Stochastic and Online Optimization COLT 2014 Online Learning with Composite Loss Functions COLT 2014 The Blinded Bandit: Learning with Adaptive Feedback NeurIPS 2014 Almost Optimal Exploration in Multi-Armed Bandits ICML 2013 Distributed Exploration in Multi-Armed Bandits NeurIPS 2013 Open Problem: Fast Stochastic Exp-Concave Optimization COLT 2013 Beating SGD: Learning SVMs in Sublinear Time NeurIPS 2011