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 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 where 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.
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}
}