Benchmarking model-based reinforcement learning T Wang, X Bao, I Clavera, J Hoang, Y Wen, E Langlois, S Zhang, G Zhang, ...
arXiv preprint arXiv:1907.02057, 2019
487 2019 Analysis of Langevin Monte Carlo from Poincaré to Log-Sobolev S Chewi, MA Erdogdu, MB Li, R Shen, M Zhang
arXiv preprint arXiv:2112.12662, 2021
128 2021 Towards a theory of non-log-concave sampling: first-order stationarity guarantees for langevin monte carlo K Balasubramanian, S Chewi, MA Erdogdu, A Salim, S Zhang
Conference on Learning Theory, 2896-2923, 2022
78 2022 Convergence of Langevin Monte Carlo in chi-squared and Rényi divergence MA Erdogdu, R Hosseinzadeh, S Zhang
International Conference on Artificial Intelligence and Statistics, 8151-8175, 2022
45 2022 One-shot pruning of recurrent neural networks by jacobian spectrum evaluation MS Zhang, B Stadie
arXiv preprint arXiv:1912.00120, 2019
43 2019 Improved discretization analysis for underdamped Langevin Monte Carlo S Zhang, S Chewi, M Li, K Balasubramanian, MA Erdogdu
The Thirty Sixth Annual Conference on Learning Theory, 36-71, 2023
38 2023 Sampling from the Mean-Field Stationary Distribution Y Kook, MS Zhang, S Chewi, MA Erdogdu, MB Li
arXiv preprint arXiv:2402.07355, 2024
11 2024 Convergence and optimality of policy gradient methods in weakly smooth settings MS Zhang, MA Erdogdu, A Garg
Proceedings of the AAAI Conference on Artificial Intelligence 36 (8), 9066-9073, 2022
8 2022 Tight regret and complexity bounds for thompson sampling via langevin monte carlo T Huix, M Zhang, A Durmus
International Conference on Artificial Intelligence and Statistics, 8749-8770, 2023
7 2023 In-and-Out: Algorithmic Diffusion for Sampling Convex Bodies Y Kook, SS Vempala, MS Zhang
arXiv preprint arXiv:2405.01425, 2024
6 2024 Uniform-in- S Chewi, A Nitanda, MS Zhang
arXiv preprint arXiv:2409.10440, 2024
2 2024 Renyi-infinity constrained sampling with Y Kook, MS Zhang
arXiv preprint arXiv:2407.12967, 2024
2 2024 Covariance estimation using markov chain Monte Carlo Y Kook, MS Zhang
arXiv preprint arXiv:2410.17147, 2024
1 2024 
Murat A. ErdogduUniversity of TorontoAdresse e-mail validée de stanford.edu