A sharp oracle inequality for Graph-Slope

Abstract : Following recent success on the analysis of the Slope estimator, we provide a sharp oracle inequality in term of prediction error for Graph-Slope, a generalization of Slope to signals observed over a graph. In addition to improving upon best results obtained so far for the Total Variation denoiser (also referred to as Graph-Lasso or Generalized Lasso), we propose an efficient algorithm to compute Graph-Slope. The proposed algorithm is obtained by applying the forward-backward method to the dual formulation of the Graph-Slope optimization problem. We also provide experiments showing the interest of the method.
Type de document :
Pré-publication, Document de travail
2017
Liste complète des métadonnées

Littérature citée [36 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-01544680
Contributeur : Samuel Vaiter <>
Soumis le : jeudi 22 juin 2017 - 00:12:56
Dernière modification le : mardi 4 juillet 2017 - 13:24:22

Fichier

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

Identifiants

  • HAL Id : hal-01544680, version 1

Citation

Pierre Bellec, Joseph Salmon, Samuel Vaiter. A sharp oracle inequality for Graph-Slope. 2017. 〈hal-01544680〉

Partager

Métriques

Consultations de
la notice

132

Téléchargements du document

21