36
5
v1v2 (latest)

Quantitative Weak Convergence for Discrete Stochastic Processes

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.

View on arXiv
Comments on this paper