English

A probability approximation framework: Markov process approach

Probability 2022-06-15 v3

Abstract

We view the classical Lindeberg principle in a Markov process setting to establish a probability approximation framework by the associated It\^{o}'s formula and Markov operator. As applications, we study the error bounds of the following three approximations: approximating a family of online stochastic gradient descents (SGDs) by a stochastic differential equation (SDE) driven by multiplicative Brownian motion, Euler-Maruyama (EM) discretization for multi-dimensional Ornstein-Uhlenbeck stable process, and multivariate normal approximation. All these error bounds are in Wasserstein-1 distance.

Keywords

Cite

@article{arxiv.2011.10985,
  title  = {A probability approximation framework: Markov process approach},
  author = {Peng Chen and Qi-Man Shao and Lihu Xu},
  journal= {arXiv preprint arXiv:2011.10985},
  year   = {2022}
}

Comments

Accepted by Annals of Applied Probability

R2 v1 2026-06-23T20:25:27.810Z