hal-00461580, version 3
Mirror averaging with sparsity priors
Bernoulli 18, 3 (2012) 914-944
Résumé : 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.
- 1 :
- INSEE – École Nationale de la Statistique et de l'Administration Économique
- 2 :
- CSTB – Ecole des Ponts ParisTech – Université Paris-Est Créteil Val-de-Marne (UPEC)
- 3 :
- Université Paris-Est Marne-la-Vallée (UPEMLV) – ESIEE – Ecole des Ponts ParisTech – Fédération de Recherche Bézout – CNRS : UMR8049
- 4 :
- CNRS : UMR7599 – Université Pierre et Marie Curie [UPMC] - Paris VI – Université Paris VII - Paris Diderot
- Domaine : Mathématiques/Statistiques
Statistiques/Théorie - Mots-clés : Mirror averaging – progressive mixture – sparsity – aggregation of estimators – oracle inequalities
- Versions disponibles : v1 (05-03-2010) v2 (25-11-2010) v3 (27-07-2012)
- hal-00461580, version 3
- http://hal.archives-ouvertes.fr/hal-00461580
- oai:hal.archives-ouvertes.fr:hal-00461580
- Contributeur :
- Soumis le : Vendredi 27 Juillet 2012, 00:08:51
- Dernière modification le : Jeudi 21 Mars 2013, 22:23:09



Documents associés

Exporter