Uri Sherman

I am an artificial intelligence researcher with interests in reinforcement learning, optimization and learning theory, and a solid background in building large-scale software systems. Currently, I am a research team lead at doubleAI, where we work on LLM post-training for multi-turn agentic reasoning tasks.

I recently completed my PhD at Tel Aviv University, where I was fortunate to be advised by Prof. Tomer Koren and Prof. Yishay Mansour. Prior to that, I spent several years in engineering and management positions in the private sector. I obtained my B.Sc. in Mathematics from Tel Aviv University, and an M.Sc. in Computer Science from the Weizmann Institute of Science, where I worked under the supervision of Prof. Uriel Feige.

Feel free to drop me a line if you’d like to chat about research, or if you think we might enjoy working together.

urishe@gmail.com Google Scholar LinkedIn
Home
Preprints

  • Convergence and Sample Complexity of First-Order Methods for Agnostic Reinforcement Learning
    Uri Sherman, Tomer Koren, Yishay Mansour

[Arxiv]
Publications

  • The Hidden Cost of Approximation in Online Mirror Descent
    Ofir Schlisselberg, Uri Sherman, Tomer Koren, Yishay Mansour
    COLT 2026

[Arxiv]

  • From Continual Learning to SGD and Back: Better Rates for Continual Linear Models
    Itay Evron*, Ran Levinstein*, Matan Schliserman*, Uri Sherman*, Tomer Koren, Daniel Soudry, Nathan Srebro
    ALT 2026

[Arxiv]

  • Fast Last-Iterate Convergence of SGD in the Smooth Interpolation Regime
    Amit Attia*, Matan Schliserman*, Uri Sherman, Tomer Koren
    NeurIPS 2025

[Arxiv]

  • Optimal Rates in Continual Linear Regression via Increasing Regularization
    Ran Levinstein*, Amit Attia*, Matan Schliserman*, Uri Sherman*, Tomer Koren, Daniel Soudry, Itay Evron
    NeurIPS 2025

[Arxiv]

  • Convergence of Policy Mirror Descent Beyond Compatible Function Approximation
    Uri Sherman, Tomer Koren, Yishay Mansour
    ICML 2025

[Arxiv]
[Arxiv]

  • Rate-Optimal Policy Optimization for Linear Markov Decision Processes
    Uri Sherman, Alon Cohen, Tomer Koren, Yishay Mansour
    ICML 2024  (Oral)

[Arxiv]

  • Improved Regret for Efficient Online Reinforcement Learning with Linear Function Approximation
    Uri Sherman, Tomer Koren, Yishay Mansour
    ICML 2023

[Arxiv]

  • Regret Minimization and Convergence to Equilibria in General-sum Markov Games
    Liad Erez*, Tal Lancewicki*, Uri Sherman*, Tomer Koren, Yishay Mansour
    ICML 2023

[Arxiv]

  • Benign Underfitting of Stochastic Gradient Descent
    Tomer Koren*, Roi Livni*, Yishay Mansour*, Uri Sherman*
    NeurIPS 2022

[Arxiv]

  • Optimal Rates for Random Order Online Optimization
    Uri Sherman, Tomer Koren, Yishay Mansour
    NeurIPS 2021  (Oral)

[Arxiv]

  • Lazy OCO: Online Convex Optimization on a Switching Budget
    Uri Sherman, Tomer Koren
    COLT 2021

[Arxiv]
(* indicates equal contribution or alphabetical ordering)
Teaching

  • Introduction to Optimization for Computer Science , Tel Aviv University, Spring Semester, 2022-2025 (TA)

  • Workshop in Machine Learning , Tel Aviv University, Spring Semester, 2024 (TA)