Skip to Main content Skip to Navigation
Conference papers

A Universal Catalyst for First-Order Optimization

Hongzhou Lin 1 Julien Mairal 1 Zaid Harchaoui 2, 1
1 LEAR - Learning and recognition in vision
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, Grenoble INP - Institut polytechnique de Grenoble - Grenoble Institute of Technology
Abstract : We introduce a generic scheme for accelerating first-order optimization methods in the sense of Nesterov, which builds upon a new analysis of the accelerated proximal point algorithm. Our approach consists of minimizing a convex objective by approximately solving a sequence of well-chosen auxiliary problems, leading to faster convergence. This strategy applies to a large class of algorithms, including gradient descent, block coordinate descent, SAG, SAGA, SDCA, SVRG, Finito/MISO, and their proximal variants. For all of these methods, we provide acceleration and explicit support for non-strongly convex objectives. In addition to theoretical speed-up, we also show that acceleration is useful in practice, especially for ill conditioned problems where we measure significant improvements.
Complete list of metadata

Cited literature [27 references]  Display  Hide  Download
Contributor : Julien Mairal Connect in order to contact the contributor
Submitted on : Sunday, October 25, 2015 - 11:15:13 AM
Last modification on : Tuesday, October 19, 2021 - 11:13:07 PM
Long-term archiving on: : Tuesday, January 26, 2016 - 10:43:23 AM


Files produced by the author(s)


  • HAL Id : hal-01160728, version 2



Hongzhou Lin, Julien Mairal, Zaid Harchaoui. A Universal Catalyst for First-Order Optimization. NIPS - Advances in Neural Information Processing Systems, Dec 2015, Montreal, Canada. pp. 3384-3392. ⟨hal-01160728v2⟩



Les métriques sont temporairement indisponibles