Independent Component Analysis by Wavelets

Abstract : We propose an ICA contrast based on the density estimation of the observed signal and its marginals by means of wavelets. The risk of the associated moment estimator is linked with approximation properties in Besov spaces. It is shown to converge faster than the at least expected minimax rate carried over from the underlying density estimations. Numerical simulations performed on some common types of densities yield very competitive results, with a high sensitivity to small departures from independence.
Type de document :
Article dans une revue
Test Publication, 2009, pp.136-155. <10.1007/s11749-007-0073-7>
Liste complète des métadonnées


https://hal.archives-ouvertes.fr/hal-00005736
Contributeur : Pascal Barbedor <>
Soumis le : jeudi 20 octobre 2005 - 19:59:24
Dernière modification le : mercredi 12 octobre 2016 - 01:02:12
Document(s) archivé(s) le : lundi 20 septembre 2010 - 11:51:05

Fichiers

Identifiants

Collections

PMA | INSMI | UPMC | USPC

Citation

Pascal Barbedor. Independent Component Analysis by Wavelets. Test Publication, 2009, pp.136-155. <10.1007/s11749-007-0073-7>. <hal-00005736v2>

Partager

Métriques

Consultations de
la notice

227

Téléchargements du document

95