A Unified View of Exact Continuous Penalties for l2-l0 Minimization

Emmanuel Soubies 1 Laure Blanc-Féraud 1 Gilles Aubert 2
1 MORPHEME - Morphologie et Images
CRISAM - Inria Sophia Antipolis - Méditerranée , IBV - Institut de Biologie Valrose : U1091, SIS - Signal, Images et Systèmes
Abstract : Numerous nonconvex continuous penalties have been proposed to approach the l0 pseudo-norm for optimization purpose. Apart from the theoretical results for convex l1 relaxation under restrictive hypothesis, only few works have been devoted to analyze the consistency, in terms of minimizers, between the l0-regularized least square functional and relaxed ones using continuous approximations. In this context, two questions are of fundamental importance: does relaxed functionals preserve global minimizers of the initial one? Does this approximation introduce unwanted new (local) minimizers? In this paper we answer these questions by deriving necessary and sufficient conditions on such l0 continuous approximations in order that each minimizer of the underlying relaxation is also a minimizer of the l2-l0 functional and that all the global minimizers of the initial functional are preserved. Hence, a general class of penalties is provided giving a unified view of exact continuous approximations of the l0-norm within the l2-l0 minimization framework. As the inferior limit of this class of penalties, we get the recently proposed CEL0 penalty. Finally, state of the art penalties, such as MCP, SCAD or Capped-l1, are analyzed according to the proposed class of exact continuous penalties.
Type de document :
Article dans une revue
SIAM Journal on Optimization, Society for Industrial and Applied Mathematics, 2017, 27 (3), 〈10.1137/16M1059333〉
Liste complète des métadonnées

Littérature citée [34 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01267701
Contributeur : Emmanuel Soubies <>
Soumis le : mardi 11 juillet 2017 - 15:47:32
Dernière modification le : lundi 4 décembre 2017 - 15:14:15

Fichier

Soubies_UnifiedView2017.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Emmanuel Soubies, Laure Blanc-Féraud, Gilles Aubert. A Unified View of Exact Continuous Penalties for l2-l0 Minimization. SIAM Journal on Optimization, Society for Industrial and Applied Mathematics, 2017, 27 (3), 〈10.1137/16M1059333〉. 〈hal-01267701v2〉

Partager

Métriques

Consultations de la notice

187

Téléchargements de fichiers

56