Newton-like inertial dynamics and proximal algorithms governed by maximally monotone operators - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2020

Newton-like inertial dynamics and proximal algorithms governed by maximally monotone operators

Hedy Attouch
Szilárd Csaba László
  • Fonction : Auteur

Résumé

The introduction of the Hessian damping in the continuous version of Nesterov's accelerated gradient method provides, by temporal discretization, fast proximal gradient algorithms where the oscillations are significantly attenuated. We will extend these results to the maximally monotone case. We rely on the technique introduced by Attouch-Peypouquet (Math. Prog. 2019), where the maximally monotone operator is replaced by its Yosida approximation with an appropriate adjustment of the regularization parameter. In a general Hilbert framework, we obtain the weak convergence of the iterates to equilibria, and the rapid convergence of the discrete velocities to zero. By specializing these algorithms to convex minimization, we obtain the convergence rate o 1/k 2 of the values, and the rapid convergence of the gradients towards zero.
Fichier principal
Vignette du fichier
SIOPT_version_April_21_2020.pdf (683.2 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02549730 , version 1 (21-04-2020)

Identifiants

  • HAL Id : hal-02549730 , version 1

Citer

Hedy Attouch, Szilárd Csaba László. Newton-like inertial dynamics and proximal algorithms governed by maximally monotone operators. 2020. ⟨hal-02549730⟩
83 Consultations
352 Téléchargements

Partager

Gmail Facebook X LinkedIn More