Alternating proximal gradient descent for nonconvex regularised problems with multiconvex coupling terms

Mila Nikolova 1 Pauline Tan 2
2 ONERA-DOTA
Palaiseau - ONERA - The French Aerospace Lab
Abstract : There has been an increasing interest in constrained nonconvex regularized block biconvex / multiconvex optimization problems. We introduce an approach that effectively exploits the biconvex / multiconvex structure of the coupling term and enables rich application-dependent regularization terms to be used. The proposed Alternating Structure-Adapted Proximal gradient descent algorithm enjoys simple well defined updates. Global convergence of the algorithm to a critical point is proved using the so-called Kurdyka-Lojasiewicz property for subanalytic functions. Moreover, we prove that a large class of useful objective functions obeying our assumptions are subanalytic and thus satisfy the Kurdyka-Lojasiewicz property.
Type de document :
Pré-publication, Document de travail
2017
Liste complète des métadonnées

Littérature citée [41 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-01492846
Contributeur : Mila Nikolova <>
Soumis le : mardi 8 août 2017 - 04:05:13
Dernière modification le : jeudi 31 août 2017 - 10:27:28

Fichier

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

Identifiants

  • HAL Id : hal-01492846, version 2

Citation

Mila Nikolova, Pauline Tan. Alternating proximal gradient descent for nonconvex regularised problems with multiconvex coupling terms. 2017. 〈hal-01492846v2〉

Partager

Métriques

Consultations de
la notice

170

Téléchargements du document

126