SAGA: A Fast Incremental Gradient Method With Support for Non-Strongly Convex Composite Objectives

Part of Advances in Neural Information Processing Systems 27 (NIPS 2014)

Bibtex Metadata Paper Reviews Supplemental

Authors

Aaron Defazio, Francis Bach, Simon Lacoste-Julien

Abstract

In this work we introduce a new fast incremental gradient method SAGA, in the spirit of SAG, SDCA, MISO and SVRG. SAGA improves on the theory behind SAG and SVRG, with better theoretical convergence rates, and support for composite objectives where a proximal operator is used on the regulariser. Unlike SDCA, SAGA supports non-strongly convex problems directly, and is adaptive to any inherent strong convexity of the problem. We give experimental results showing the effectiveness of our method.