Fast proximal methods via time scaling of damped inertial dynamics - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2018

Fast proximal methods via time scaling of damped inertial dynamics

Résumé

In a Hilbert setting, we consider a class of inertial proximal algorithms for nonsmooth convex optimization, with fast convergence properties. They can be obtained by time discretization of inertial gradient dynamics which have been rescaled in time. We will rely specifically on the recent developement linking Nesterov's accelerated method with vanishing damping inertial dynamics. Doing so, we somehow improve and obtain a dynamical interpretation of the seminal papers of Güler on the convergence rate of the proximal methods for convex optimization.
Fichier principal
Vignette du fichier
ACR, fast prox inertiel, Nov. 29, 2018.pdf (371.39 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-01939292 , version 1 (29-11-2018)

Identifiants

  • HAL Id : hal-01939292 , version 1

Citer

Hedy Attouch, Zaki Chbani, Hassan Riahi. Fast proximal methods via time scaling of damped inertial dynamics. 2018. ⟨hal-01939292⟩
111 Consultations
553 Téléchargements

Partager

Gmail Mastodon Facebook X LinkedIn More