Optimal Algorithms for Stochastic Complementary Composite Minimization

TL;DR

This paper introduces nearly optimal algorithms with new complexity bounds for stochastic complementary composite minimization, a problem involving smooth and structured convex functions with regularization, and demonstrates their effectiveness through numerical experiments.

Contribution

The paper develops the first complexity bounds and nearly optimal algorithms for stochastic complementary composite minimization, filling a significant gap in the literature.

Findings

Established novel excess risk bounds in expectation and high probability.

Proposed algorithms are nearly optimal based on new lower complexity bounds.

Numerical results show improved performance over existing methods.

Abstract

Inspired by regularization techniques in statistics and machine learning, we study complementary composite minimization in the stochastic setting. This problem corresponds to the minimization of the sum of a (weakly) smooth function endowed with a stochastic first-order oracle, and a structured uniformly convex (possibly nonsmooth and non-Lipschitz) regularization term. Despite intensive work on closely related settings, prior to our work no complexity bounds for this problem were known. We close this gap by providing novel excess risk bounds, both in expectation and with high probability. Our algorithms are nearly optimal, which we prove via novel lower complexity bounds for this class of problems. We conclude by providing numerical results comparing our methods to the state of the art.