Back to Search Start Over

Quantitative Weak Convergence for Discrete Stochastic Processes

Authors :
Cheng, Xiang
Bartlett, Peter L.
Jordan, Michael I.
Publication Year :
2019

Abstract

In this paper, we quantitative convergence in $W_2$ 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 $\tilde{O}\lrp{1/\sqrt{k}}$ where $k$ 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.

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.1902.00832
Document Type :
Working Paper