STOCHASTIC PRIMAL-DUAL HYBRID GRADIENT ALGORITHM WITH ARBITRARY SAMPLING AND IMAGING APPLICATIONS - CNRS - Centre national de la recherche scientifique Accéder directement au contenu
Article Dans Une Revue SIAM Journal on Optimization Année : 2018

STOCHASTIC PRIMAL-DUAL HYBRID GRADIENT ALGORITHM WITH ARBITRARY SAMPLING AND IMAGING APPLICATIONS

Résumé

We propose a stochastic extension of the primal-dual hybrid gradient algorithm studied by Chambolle and Pock in 2011 to solve saddle point problems that are separable in the dual variable. The analysis is carried out for general convex-concave saddle point problems and problems that are either partially smooth / strongly convex or fully smooth / strongly convex. We perform the analysis for arbitrary samplings of dual variables, and obtain known deterministic results as a special case. Several variants of our stochastic method significantly outperform the deterministic variant on a variety of imaging tasks.
Fichier principal
Vignette du fichier
main_SIOPT.pdf (2.67 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01569426 , version 1 (26-07-2017)
hal-01569426 , version 2 (18-06-2019)

Identifiants

Citer

Antonin Chambolle, Matthias J Ehrhardt, Peter Richtarik, Carola-Bibiane Schönlieb. STOCHASTIC PRIMAL-DUAL HYBRID GRADIENT ALGORITHM WITH ARBITRARY SAMPLING AND IMAGING APPLICATIONS. SIAM Journal on Optimization, 2018, 28 (4), pp.2783-2808. ⟨10.1137/17M1134834⟩. ⟨hal-01569426v2⟩
555 Consultations
494 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More