English

Approximation to stochastic variance reduced gradient Langevin dynamics by stochastic delay differential equations

Probability 2021-12-21 v2 Optimization and Control

Abstract

We study in this paper a weak approximation to stochastic variance reduced gradient Langevin dynamics by stochastic delay differential equations in Wasserstein-1 distance, and obtain a uniform error bound. Our approach is via a refined Lindeberg principle and Malliavin calculus.

Keywords

Cite

@article{arxiv.2106.04357,
  title  = {Approximation to stochastic variance reduced gradient Langevin dynamics by stochastic delay differential equations},
  author = {Peng Chen and Jianya Lu and Lihu Xu},
  journal= {arXiv preprint arXiv:2106.04357},
  year   = {2021}
}

Comments

We update the assumption and the convergence rate, which are both better than the original version

R2 v1 2026-06-24T02:57:36.104Z