A sharp oracle inequality for Graph-Slope - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Electronic Journal of Statistics Année : 2017

A sharp oracle inequality for Graph-Slope

Résumé

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 practical applicability of the method.
Fichier principal
Vignette du fichier
graphslope_oracle.pdf (4 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01544680 , version 1 (22-06-2017)

Identifiants

Citer

Pierre C. Bellec, Joseph Salmon, Samuel Vaiter. A sharp oracle inequality for Graph-Slope. Electronic Journal of Statistics , 2017, 11 (2), pp.4851-4870. ⟨10.1214/17-EJS1364⟩. ⟨hal-01544680⟩
201 Consultations
51 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More