Scholar
Tomer Koren
Google Scholar ID: wGG1voYAAAAJ
Associate Professor at Tel Aviv University
Citations & Impact
Citations
4,362
H-index
32
i10-index
61
Publications
20
Co-authors
65
list available
Contact
Publications
Resume (English only)
Academic Achievements
- Convergence and Sample Complexity of First-Order Methods for Agnostic Reinforcement Learning.
- Nearly Optimal Sample Complexity for Learning with Label Proportions.
- Benefits of Learning Rate Annealing for Tuning-Robustness in Stochastic Optimization.
- From Continual Learning to SGD and Back: Better Rates for Continual Linear Models.
- Complexity of Vector-valued Prediction: From Linear Models to Stochastic Convex Optimization.
- A General Reduction for High-Probability Analysis with General Light-Tailed Distributions.
- Fast Last-Iterate Convergence of SGD in the Smooth Interpolation Regime. (NeurIPS 2025)
- Bandit Multiclass List Classification. (NeurIPS 2025)
- Optimal Rates in Continual Linear Regression via Increasing Regularization. (NeurIPS 2025)
- Multiplicative Reweighting for Robust Neural Network Optimization. (SIAM Journal on Imaging Sciences)
- Rapid Overfitting of Multi-Pass SGD in Stochastic Convex Optimization. (ICML 2025, Spotlight)
- Convergence of Policy Mirror Descent Beyond Compatible Function Approximation. (ICML 2025)
- Faster Stochastic Optimization with Arbitrary Delays via Adaptive Asynchronous Mini-Batching. (ICML 2025)
- Nearly Optimal Sample Complexity for Learning with Label Proportions. (ICML 2025)
- Dueling Convex Optimization with General Preferences. (ICML 2025)
- Locally Optimal Descent for Dynamic Stepsize Scheduling. (AISTATS 2025)
- The Dimension Strikes Back with Gradients: Generalization of Gradient Methods in Stochastic Convex Optimization. (ALT 2025, Outstanding Paper Award; Oral presentation at OPT2024)
- Fast Rates for Bandit PAC Multiclass Classification. (NeurIPS 2024)
- Private Online Learning via Lazy Algorithms. (NeurIPS 2024)
- Rate-Optimal Policy Optimization for Linear Markov Decision Processes. (ICML 2024, Oral)
- How Free is Parameter-Free Stochastic Optimization? (ICML 2024, Spotlight)
- The Real Price of Bandit Information in Multiclass Classification. (COLT 2024)
- Faster Convergence with Multiway Preferences. (AISTATS)
Research Experience
- Serves as an Associate Professor at Tel Aviv University and a Senior Research Scientist at Google Research, Tel Aviv.
Education
- Received his PhD from the Technion—Israel Institute of Technology, where his advisor was Prof. Elad Hazan.
Background
- Associate Professor at the Blavatnik School of Computer Science, Tel Aviv University, and a Senior Research Scientist at Google Research, Tel Aviv. His research interests are in machine learning and optimization.
