2014
NeurIPS
NeurIPS 2014
SAGA: A Fast Incremental Gradient Method With Support for Non-Strongly Convex Composite Objectives
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.
🌉
Interdisciplinary Bridge
- Artificial Intelligence and Mathematics & Optimization
🐣
Hot Topic Early Bird
- stochastic gradient
Authors
Topics
Machine Learning > Optimization & Theory > Neural Network Optimization
Machine Learning > Optimization & Theory > Optimization
Mathematics & Optimization > Optimization > Continuous Optimization
Machine Learning > Optimization & Theory > Stochastic Methods
Mathematics & Optimization > Optimization > Optimization
Deep Learning > Optimization & Theory > Optimization
Mathematics & Optimization > Optimization > Convex Optimization