Improved bounds for discretization of Langevin diffusions: Near-optimal rates without convexity-Reference-Cited by-同舟云学术

Improved bounds for discretization of Langevin diffusions: Near-optimal rates without convexity

Published:2022-08-01 Issue:3 Volume:28 Page:
ISSN:1350-7265
Container-title:Bernoulli
language:
Short-container-title:Bernoulli

Author:

Mou Wenlong¹,Flammarion Nicolas²,Wainwright Martin J.¹,Bartlett Peter L.¹

Affiliation:

1. Department of EECS, UC Berkeley, Cory Hall, Berkeley, CA, 94720, USA

2. School of Computer and Communication Sciences, EPFL, INJ 336, Station 14, CH-1015 Lausanne, Switzerland

Publisher

Bernoulli Society for Mathematical Statistics and Probability

Subject

Statistics and Probability

Reference58 articles.

1. Alfonsi, A., Jourdain, B. and Kohatsu-Higa, A. (2015). Optimal transport bounds between the time-marginals of a multidimensional diffusion and its Euler scheme. Electron. J. Probab. 20 no. 70, 31. 10.1214/EJP.v20-4195

2. Bakry, D., Barthe, F., Cattiaux, P. and Guillin, A. (2008). A simple proof of the Poincaré inequality for a large class of probability measures including the log-concave case. Electron. Commun. Probab. 13 60–66. 10.1214/ECP.v13-1352

3. Bakry, D. and Émery, M. (1985). Diffusions hypercontractives. In Séminaire de Probabilités, XIX, 1983/84. Lecture Notes in Math. 1123 177–206. Berlin: Springer. 10.1007/BFb0075847

4. Bernton, E. (2018) Langevin Monte Carlo and JKO splitting. In Proceedings of the 31st Conference on Learning Theory. Proceedings of Machine Learning Research 75 1777–1798. PMLR.

5. Bolley, F. and Villani, C. (2005). Weighted Csiszár-Kullback-Pinsker inequalities and applications to transportation inequalities. Ann. Fac. Sci. Toulouse Math. (6) 14 331–352.

Cited by 6 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Analysis of Langevin Monte Carlo from Poincaré to Log-Sobolev;Foundations of Computational Mathematics;2024-07-26

2. (Non)-penalized multilevel methods for non-uniformly log-concave distributions;Electronic Journal of Probability;2024-01-01

3. Global Optimization via Schrödinger–Föllmer Diffusion;SIAM Journal on Control and Optimization;2023-09-28

4. Separation of scales and a thermodynamic description of feature learning in some CNNs;Nature Communications;2023-02-17

5. Unadjusted Langevin algorithm with multiplicative noise: Total variation and Wasserstein bounds;The Annals of Applied Probability;2023-02-01