Direct Acceleration of SAGA using Sampled Negative Momentum

[edit]

Kaiwen Zhou, Qinghua Ding, Fanhua Shang, James Cheng, Danli Li, Zhi-Quan Luo ;
Proceedings of Machine Learning Research, PMLR 89:1602-1610, 2019.

Abstract

Variance reduction is a simple and effective technique that accelerates convex (or non-convex) stochastic optimization. Among existing variance reduction methods, SVRG and SAGA adopt unbiased gradient estimators and are the most popular variance reduction methods in recent years. Although various accelerated variants of SVRG (e.g., Katyusha and Acc-Prox-SVRG) have been proposed, the direct acceleration of SAGA still remains unknown. In this paper, we propose a directly accelerated variant of SAGA using a novel Sampled Negative Momentum (SSNM), which achieves the best known oracle complexity for strongly convex problems (with known strong convexity parameter). Consequently, our work fills the void of directly accelerated SAGA.

Related Material