Pré-Publication, Document De Travail Année : 2019

Accelerated iterative regularization via dual diagonal descent

Résumé

We propose and analyze an accelerated iterative dual diagonal descent algorithm for the solution of linear inverse problems with general regularization and data-fit functions. In particular , we develop an inertial approach of which we analyze both convergence and stability. Using tools from inexact proximal calculus, we prove early stopping results with optimal convergence rates for additive data-fit terms as well as more general cases, such as the Kullback-Leibler divergence, for which different type of proximal point approximations hold.

Fichier principal
Vignette du fichier
I3D.pdf (568.1 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence
Loading...

Dates et versions

hal-02423682 , version 1 (24-12-2019)

Licence

Identifiants

  • HAL Id : hal-02423682 , version 1

Citer

Luca Calatroni, Guillaume Garrigos, Lorenzo Rosasco, Silvia Villa. Accelerated iterative regularization via dual diagonal descent. 2019. ⟨hal-02423682⟩
283 Consultations
314 Téléchargements

Partager

  • More