On the Convergence Rates of Proximal Splitting Algorithms - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2014

On the Convergence Rates of Proximal Splitting Algorithms

Résumé

In this work, we first provide iteration–complexity bounds (pointwise and ergodic) for the inexact Krasnosel'ski˘ ı–Mann iteration built from nonexpansive operators. Moreover, un-der an appropriate regularity assumption on the fixed point operator, local linear convergence rate is also established. These results are then applied to analyze the convergence rate of various proximal splitting methods in the litera-ture, which includes the Forward–Backward, generalized Forward–Backward, Douglas–Rachford, ADMM and some primal–dual splitting methods. For these algorithms, we develop easily verifiable termination criteria for finding an approximate solution, which is a generalization of the ter-mination criterion for the classical gradient descent method. We illustrate the usefulness of our results on a large class of problems in signal and image processing.
Fichier principal
Vignette du fichier
icip-rates-2014.pdf (286.42 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01080059 , version 1 (04-11-2014)

Identifiants

  • HAL Id : hal-01080059 , version 1

Citer

Jingwei Liang, Jalal M. Fadili, Gabriel Peyré. On the Convergence Rates of Proximal Splitting Algorithms. IEEE International Conference on Image Processing (ICIP 2014), Oct 2014, Paris, France. ⟨hal-01080059⟩
154 Consultations
187 Téléchargements

Partager

Gmail Facebook X LinkedIn More