Inexact proximal stochastic gradient method for convex composite optimization

Document Type

Article

Publication Date

12-1-2017

Abstract

We study an inexact proximal stochastic gradient (IPSG) method for convex composite optimization, whose objective function is a summation of an average of a large number of smooth convex functions and a convex, but possibly nonsmooth, function. Variance reduction techniques are incorporated in the method to reduce the stochastic gradient variance. The main feature of this IPSG algorithm is to allow solving the proximal subproblems inexactly while still keeping the global convergence with desirable complexity bounds. Different subproblem stopping criteria are proposed. Global convergence and the component gradient complexity bounds are derived for the both cases when the objective function is strongly convex or just generally convex. Preliminary numerical experiment shows the overall efficiency of the IPSG algorithm.

Publication Source (Journal or Book title)

Computational Optimization and Applications

First Page

579

Last Page

618

This document is currently not available here.

Share

COinS