On Representer Theorems and Convex Regularization - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Article Dans Une Revue SIAM Journal on Optimization Année : 2019

On Representer Theorems and Convex Regularization

Résumé

We establish a general principle which states that regularizing an inverse problem with a convex function yields solutions which are convex combinations of a small number of atoms. These atoms are identified with the extreme points and elements of the extreme rays of the regularizer level sets. An extension to a broader class of quasi-convex regularizers is also discussed. As a side result, we characterize the minimizers of the total gradient variation, which was still an unresolved problem.
Fichier principal
Vignette du fichier
BCDDGW_18.pdf (344.17 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-01823135 , version 1 (25-06-2018)
hal-01823135 , version 2 (16-07-2018)
hal-01823135 , version 3 (26-11-2018)

Identifiants

Citer

Claire Boyer, Antonin Chambolle, Yohann de Castro, Vincent Duval, Frédéric de Gournay, et al.. On Representer Theorems and Convex Regularization. SIAM Journal on Optimization, 2019, 29 (2), pp.1260-1281. ⟨10.1137/18M1200750⟩. ⟨hal-01823135v3⟩
1047 Consultations
839 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More