Back to Search Start Over

Contracting Proximal Methods for Smooth Convex Optimization

Authors :
Doikov, Nikita
Nesterov, Yurii
UCL - SSH/LIDAM/CORE - Center for operations research and econometrics
Source :
SIAM Journal on Optimization, Vol. 30, no.4, p. 3146-3169 (2020), SIAM Journal on Optimization
Publication Year :
2020
Publisher :
Society for Industrial & Applied Mathematics (SIAM), 2020.

Abstract

In this paper, we propose new accelerated methods for smooth convex optimization, called contracting proximal methods. At every step of these methods, we need to minimize a contracted version of the objective function augmented by a regularization term in the form of Bregman divergence. We provide global convergence analysis for a general scheme admitting inexactness in solving the auxiliary subproblem. In the case of using for this purpose high-order tensor methods, we demonstrate an acceleration effect for both convex and uniformly convex composite objective functions. Thus, our construction explains acceleration for methods of any order starting from one. The augmentation of the number of calls of oracle due to computing the contracted proximal steps is limited by the logarithmic factor in the worst-case complexity bound.

Details

ISSN :
10957189 and 10526234
Volume :
30
Database :
OpenAIRE
Journal :
SIAM Journal on Optimization
Accession number :
edsair.doi.dedup.....92b7b18087d9d9cdc17af478e6af7b14