Maxisets for Model Selection - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Constructive Approximation Année : 2010

Maxisets for Model Selection

Résumé

We address the statistical issue of determining the maximal spaces (maxisets) where model selection procedures attain a given rate of convergence. By considering first general dictionaries, then orthonormal bases, we characterize these maxisets in terms of approximation spaces. These results are illustrated by classical choices of wavelet model collections. For each of them, the maxisets are described in terms of functional spaces. We take a special care of the issue of calculability and measure the induced loss of performance in terms of maxisets.
Fichier principal
Vignette du fichier
ModelMaxiFinal.pdf (366.04 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-00259253 , version 2 (27-02-2008)
hal-00259253 , version 3 (16-12-2008)
hal-00259253 , version 1 (21-10-2011)

Identifiants

Citer

Florent Autin, Erwan Le Pennec, Jean-Michel Loubes, Vincent Rivoirard. Maxisets for Model Selection. Constructive Approximation, 2010, 31 (2), pp.195-229. ⟨10.1007/s00365-009-9062-2⟩. ⟨hal-00259253v3⟩
853 Consultations
251 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More