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

Aaron Defazio, Francis Bach, Simon Lacoste-Julien

Publication date: 1 July 2014

Abstract: In this work we introduce a new optimisation method called SAGA in the spirit of SAG, SDCA, MISO and SVRG, a set of recently proposed incremental gradient algorithms with fast linear convergence rates. SAGA improves on the theory behind SAG and SVRG, with better theoretical convergence rates, and has 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.

Has companion code repository: https://github.com/adefazio/point-saga

This page was built for publication: SAGA: A Fast Incremental Gradient Method With Support for Non-Strongly Convex Composite Objectives

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6252788)