Volgen
Uri Sherman
Uri Sherman
School of Computer Science, Tel Aviv University
Geverifieerd e-mailadres voor mail.tau.ac.il - Homepage
Titel
Geciteerd door
Geciteerd door
Jaar
Regret minimization and convergence to equilibria in general-sum markov games
L Erez, T Lancewicki, U Sherman, T Koren, Y Mansour
International Conference on Machine Learning, 9343-9373, 2023
182023
Benign underfitting of stochastic gradient descent
T Koren, R Livni, Y Mansour, U Sherman
Advances in Neural Information Processing Systems 35, 19605-19617, 2022
142022
Lazy oco: Online convex optimization on a switching budget
U Sherman, T Koren
Conference on Learning Theory, 3972-3988, 2021
142021
Improved regret for efficient online reinforcement learning with linear function approximation
U Sherman, T Koren, Y Mansour
International Conference on Machine Learning, 31117-31150, 2023
132023
Optimal rates for random order online optimization
U Sherman, T Koren, Y Mansour
Advances in Neural Information Processing Systems 34, 2097-2108, 2021
92021
Rate-optimal policy optimization for linear markov decision processes
U Sherman, A Cohen, T Koren, Y Mansour
arXiv preprint arXiv:2308.14642, 2023
52023
The Dimension Strikes Back with Gradients: Generalization of Gradient Methods in Stochastic Convex Optimization
M Schliserman, U Sherman, T Koren
arXiv preprint arXiv:2401.12058, 2024
12024
Het systeem kan de bewerking nu niet uitvoeren. Probeer het later opnieuw.
Artikelen 1–7