Non-Asymptotic Guarantees for Sampling by Stochastic Gradient Descent

Abstract

Sampling from various kinds of distributions is an issue of paramount importance in statistics since it is often the key ingredient for constructing estimators, test procedures or confidence intervals. In many situations, the exact sampling from a given distribution is impossible or computationally expensive and, therefore, one needs to resort to approximate sampling strategies. However, it is only very recently that a mathematical theory providing non-asymptotic guarantees for approximate sampling problem in the high-dimensional settings started to be developed. In this paper we introduce a new mathematical framework that helps to analyze the Stochastic Gradient Descent as a method of sampling, closely related to Langevin Monte-Carlo.