Convergence rate of inertial Forward-Backward algorithm beyond Nesterov's rule

Abstract : In this paper we study the convergence of an Inertial Forward-Backward algorithm, with a particular choice of an over-relaxation term. In particular we show that for a sequence of overrrelaxation parameters, that do not satisfy Nesterov’s rule one can still expect some relatively fast convergence properties for the objective function. In addition we complement this work by studying the convergence of the algorithm in the case where the proximal operator is inexactly computed with the presence of some errors and we give sufficient conditions over these errors in order to obtain some convergence properties for the objective function .
Type de document :
Pré-publication, Document de travail
2017
Liste complète des métadonnées


https://hal.archives-ouvertes.fr/hal-01551873
Contributeur : Vasileios Apidopoulos <>
Soumis le : vendredi 30 juin 2017 - 16:53:22
Dernière modification le : samedi 1 juillet 2017 - 01:06:33

Fichier

Endiscret4.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01551873, version 1

Collections

Citation

Vassilis Apidopoulos, Jean-François Aujol, Charles Dossal. Convergence rate of inertial Forward-Backward algorithm beyond Nesterov's rule. 2017. <hal-01551873>

Partager

Métriques

Consultations de
la notice

248

Téléchargements du document

79