Stochastic Quasi-Fejér Block-Coordinate Fixed Point Iterations With Random Sweeping II: Mean-Square and Linear Convergence

Abstract : Reference [11] investigated the almost sure weak convergence of block-coordinate fixed point algorithms and discussed their applications to nonlinear analysis and optimization. This algorith-mic framework features random sweeping rules to select arbitrarily the blocks of variables that are activated over the course of the iterations and it allows for stochastic errors in the evaluation of the operators. The present paper establishes results on the mean-square and linear convergence of the iterates. Applications to monotone operator splitting and proximal optimization algorithms are presented.
Type de document :
Pré-publication, Document de travail
2018
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01964582
Contributeur : Jean-Christophe Pesquet <>
Soumis le : samedi 22 décembre 2018 - 18:04:26
Dernière modification le : samedi 5 janvier 2019 - 01:12:11

Fichier

mp4.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01964582, version 1

Citation

Patrick Combettes, Jean-Christophe Pesquet. Stochastic Quasi-Fejér Block-Coordinate Fixed Point Iterations With Random Sweeping II: Mean-Square and Linear Convergence. 2018. 〈hal-01964582〉

Partager

Métriques

Consultations de la notice

18

Téléchargements de fichiers

12