Mirror averaging with sparsity priors

Abstract : We consider the problem of aggregating the elements of a (possibly infinite) dictionary for building a decision procedure, that aims at minimizing a given criterion. Along with the dictionary, an independent identically distributed training sample is available, on which the performance of a given procedure can be tested. In a fairly general set-up, we establish an oracle inequality for the Mirror Averaging aggregate based on any prior distribution. This oracle inequality is applied in the context of sparse coding for different problems of statistics and machine learning such as regression, density estimation and binary classification.
Type de document :
Article dans une revue
Bernoulli, Bernoulli Society for Mathematical Statistics and Probability, 2012, 18 (3), pp.914-944. <10.3150/11-BEJ361>
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-00461580
Contributeur : Arnak Dalalyan <>
Soumis le : vendredi 27 juillet 2012 - 00:08:51
Dernière modification le : jeudi 9 février 2017 - 15:03:05
Document(s) archivé(s) le : dimanche 28 octobre 2012 - 02:35:07

Fichiers

Bernoulli-revised5.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Citation

Arnak S. Dalalyan, Alexandre Tsybakov. Mirror averaging with sparsity priors. Bernoulli, Bernoulli Society for Mathematical Statistics and Probability, 2012, 18 (3), pp.914-944. <10.3150/11-BEJ361>. <hal-00461580v3>

Partager

Métriques

Consultations de
la notice

214

Téléchargements du document

96