← Authors

Tomer Koren

70 papers · 2011–2025 · 5 conferences · across top CS/AI conferences

Achievements

🐣 Hot Topic Early Bird 🐝 Cross-Pollinator (14) πŸƒ Academic Marathon (14) 🌍 Conference Polyglot (5) 🌈 Renaissance Researcher (5) πŸŒ‰ Interdisciplinary Bridge πŸ—ΊοΈ Taxonomy Completionist (14) 🧭 Keyword Pioneer 🏠 Conference Loyalist (26) πŸ† Keyword Champion πŸ”¬ Deep Specialist (29) 🀝 Dynamic Duo (21) πŸš€ Conference Pioneer ⚑ Prolific Year (6) πŸ”₯ Unstoppable (13) ❓ The Questioner (2) πŸ“ˆ Trend Setter πŸ’Ž Century Club (70) πŸ—ƒοΈ Keyword Collector (53)

Conferences

NIPS (26) ICML (23) COLT (18) AISTATS (2) ALT (1)

Top co-authors

Yishay Mansour (21) Roi Livni (12) Alon Cohen (12) Uri Sherman (8) Kunal Talwar (8) Elad Hazan (5) Amit Attia (5) Ofer Dekel (5) Idan Amir (4) Liad Erez (4)

Research topics

Differential Privacy (1)

Keywords

regret bound (28) online learning (18) stochastic optimization (13) multi-armed bandit (12) stochastic gradient descent (10) convex optimization (7) gradient descent (6) online convex optimization (6) convergence rate (6) regret minimization (4) generalization bound (4) minimax regret (4) algorithmic stability (3) generalization error (3) mirror descent (3) stochastic convex optimization (3) learning theory (3) linear quadratic regulator (3) optimal control (3) online optimization (3)

Papers

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