A Proximal Approach for Solving Matrix Optimization Problems Involving a Bregman Divergence

Alessandro Benfenati 1 Emilie Chouzenoux 1, 2 Jean-Christophe Pesquet 2
1 LIGM - Laboratoire d'Informatique Gaspard-Monge
2 GALEN - Organ Modeling through Extraction, Representation and Understanding of Medical Image Content
Inria Saclay - Ile de France, Ecole Centrale Paris
Abstract : In recent years, there has been a growing interest in problems such as shape classification, gene expression inference, inverse covariance estimation. Problems of this kind have a common underlining mathematical model, which involves the minimization in a matrix space of a Bregman divergence function coupled with a linear term and a regularization term. We present an application of the Douglas-Rachford algorithm which allows to easily solve the optimization problem.
Type de document :
Communication dans un congrès
BASP 2017 - International Biomedical and Astronomical Signal Processing Frontiers workshop, Jan 2017, villars-sur-oulon, Switzerland. 2017
Liste complète des métadonnées

Littérature citée [8 références]  Voir  Masquer  Télécharger
https://hal.archives-ouvertes.fr/hal-01613292
Contributeur : Emilie Chouzenoux <>
Soumis le : mardi 10 octobre 2017 - 11:34:59
Dernière modification le : jeudi 5 juillet 2018 - 14:45:42
Document(s) archivé(s) le : jeudi 11 janvier 2018 - 13:14:08

Fichier

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

Identifiants

  • HAL Id : hal-01613292, version 1

Collections

ANRGRAPHSIP | INRIA2017 | INRIA | UPEC-UPEM | UNIV-PARIS-SACLAY | LIGM_SIGNAL | ENPC | LIGM | PARISTECH | CENTRALESUPELEC | CVN | ESIEE-PARIS

Citation

Alessandro Benfenati, Emilie Chouzenoux, Jean-Christophe Pesquet. A Proximal Approach for Solving Matrix Optimization Problems Involving a Bregman Divergence. BASP 2017 - International Biomedical and Astronomical Signal Processing Frontiers workshop, Jan 2017, villars-sur-oulon, Switzerland. 2017. 〈hal-01613292〉

Exporter

BibTeX TEI DC DCterms EndNote

Partager

Métriques

Consultations de la notice

208

Téléchargements de fichiers

62

Contact

support.ccsd.cnrs.fr
hal.support@ccsd.cnrs.fr
Logo CCSD