Catalyst Acceleration for First-order Convex Optimization: from Theory to Practice - Inria - Institut national de recherche en sciences et technologies du numérique
Journal Articles Journal of Machine Learning Research Year : 2018

Catalyst Acceleration for First-order Convex Optimization: from Theory to Practice

Abstract

We introduce a generic scheme for accelerating gradient-based optimization methods in the sense of Nesterov. The approach, called Catalyst, builds upon the inexact accelerated proximal point algorithm for minimizing a convex objective function, and consists of approximately solving a sequence of well-chosen auxiliary problems, leading to faster convergence. One of the key to achieve acceleration in theory and in practice is to solve these sub-problems with appropriate accuracy by using the right stopping criterion and the right warm-start strategy. In this paper, we give practical guidelines to use Catalyst and present a comprehensive theoretical analysis of its global complexity. We show that Catalyst applies to a large class of algorithms, including gradient descent, block coordinate descent, incremental algorithms such as 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. We conclude with extensive experiments showing that acceleration is useful in practice, especially for ill-conditioned problems.
Fichier principal
Vignette du fichier
17-748.pdf (1.62 Mo) Télécharger le fichier
Origin Files produced by the author(s)
Loading...

Dates and versions

hal-01664934 , version 1 (21-12-2017)
hal-01664934 , version 2 (19-06-2018)

Identifiers

  • HAL Id : hal-01664934 , version 2

Cite

Hongzhou Lin, Julien Mairal, Zaid Harchaoui. Catalyst Acceleration for First-order Convex Optimization: from Theory to Practice. Journal of Machine Learning Research, 2018, 18 (1), pp.7854-7907. ⟨hal-01664934v2⟩
637 View
240 Download

Share

More