Contracting proximal methods for smooth convex optimization

Nikita, Doikov () and Yurii, Nesterov
Additional contact information
Nikita, Doikov: Université catholique de Louvain, CORE, Belgium

No 2019027, LIDAM Discussion Papers CORE from Université catholique de Louvain, Center for Operations Research and Econometrics (CORE)

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 function. 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 bounds.

Keywords: convex optimization; proximal method; accelerated methods; global complexity bounds; high-order algorithms (search for similar items in EconPapers)
Date: 2019-12-17
References: Add references at CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
https://sites.uclouvain.be/core/publications/coredp/coredp2019.html (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:cor:louvco:2019027

Access Statistics for this paper

More papers in LIDAM Discussion Papers CORE from Université catholique de Louvain, Center for Operations Research and Econometrics (CORE) Voie du Roman Pays 34, 1348 Louvain-la-Neuve (Belgium). Contact information at EDIRC.
Bibliographic data for series maintained by Alain GILLIS ().