English

Quantitative Weak Convergence for Discrete Stochastic Processes

Statistics Theory 2019-07-03 v2 Machine Learning Machine Learning Statistics Theory

Abstract

In this paper, we quantitative convergence in W2W_2 for a family of Langevin-like stochastic processes that includes stochastic gradient descent and related gradient-based algorithms. Under certain regularity assumptions, we show that the iterates of these stochastic processes converge to an invariant distribution at a rate of O~\lrp1/k\tilde{O}\lrp{1/\sqrt{k}} where kk is the number of steps; this rate is provably tight up to log factors. Our result reduces to a quantitative form of the classical Central Limit Theorem in the special case when the potential is quadratic.

Keywords

Cite

@article{arxiv.1902.00832,
  title  = {Quantitative Weak Convergence for Discrete Stochastic Processes},
  author = {Xiang Cheng and Peter L. Bartlett and Michael I. Jordan},
  journal= {arXiv preprint arXiv:1902.00832},
  year   = {2019}
}
R2 v1 2026-06-23T07:30:35.164Z