activity
20222025
most citedA sharp uniform-in-time error estimate for Stochastic Gradient Langevin Dynamics

1 citations · 1 across the 6 of their papers we have counts for

collaborators
Showing math.PRShow all

3 papers · 1 filter

math.PR2023

Propagation of chaos in path spaces via information theory

Lei Li, Yuelin Wang, Yuliang Wang

Propagation of chaos for interacting particle systems has been an active research topic over decades. We propose an alternative approach to study the mean-field limit of the stocha…

math.PR2023

Geometric ergodicity of SGLD via reflection coupling

Lei Li, Jian-Guo Liu, Yuliang Wang

We consider the geometric ergodicity of the Stochastic Gradient Langevin Dynamics (SGLD) algorithm under nonconvexity settings. Via the technique of reflection coupling, we prove t…

math.PR2022★ 1 cited

A sharp uniform-in-time error estimate for Stochastic Gradient Langevin Dynamics

Lei Li, Yuliang Wang

We establish a sharp uniform-in-time error estimate for the Stochastic Gradient Langevin Dynamics (SGLD), which is a widely-used sampling algorithm. Under mild assumptions, we obta…