Iteration-Complexity of a Generalized Forward Backward Splitting Algorithm - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2014

Iteration-Complexity of a Generalized Forward Backward Splitting Algorithm

Résumé

In this paper, we analyze the iteration-complexity of Generalized Forward-Backward (GFB) splitting algorithm, as proposed in [2], for minimizing a large class of composite objectives on a Hilbert space, where f has a Lipschitz-continuous gradient and the hi's are simple (i.e. their proximity operators are easy to compute). We derive iteration-complexity bounds (pointwise and ergodic) for the inexact version of GFB to obtain an approximate solution based on an easily verifiable termination criterion. Along the way, we prove complexity bounds for relaxed and inexact fixed point iterations built from composition of nonexpansive averaged operators. These results apply more generally to GFB when used to find a zero of a sum of n>0 maximal monotone operators and a co-coercive operator on a Hilbert space. The theoretical findings are exemplified with experiments on video processing.
Fichier principal
Vignette du fichier
icassprateGFB.pdf (437.78 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01073917 , version 1 (27-10-2014)

Identifiants

  • HAL Id : hal-01073917 , version 1

Citer

Jingwei Liang, Jalal M. Fadili, Gabriel Peyré. Iteration-Complexity of a Generalized Forward Backward Splitting Algorithm. ICASSP'14, May 2014, Florence, Italy. 5 pp. ⟨hal-01073917⟩
170 Consultations
64 Téléchargements

Partager

Gmail Facebook X LinkedIn More