Blockwise SVD with error in the operator and application to blind deconvolution

Abstract : We consider linear inverse problems in a nonparametric statistical framework. Both the signal and the operator are unknown and subject to error measurements. We establish minimax rates of convergence under squared error loss when the operator admits a blockwise singular value decomposition (blockwise SVD) and the smoothness of the signal is measured in a Sobolev sense. We construct a nonlinear procedure adapting simultaneously to the unknown smoothness of both the signal and the operator and achieving the optimal rate of convergence to within logarithmic terms. When the noise level in the operator is dominant, by taking full advantage of the blockwise SVD property, we demonstrate that the block SVD procedure outperforms classical methods based on Galerkin projection or nonlinear wavelet thresholding. We subsequently apply our abstract framework to the specific case of blind deconvolution on the torus and on the sphere.
Type de document :
Article dans une revue
Electronic journal of statistics , Shaker Heights, OH : Institute of Mathematical Statistics, 2012, 6, pp.2274-2308. 〈10.1214/12-EJS745〉
Liste complète des métadonnées

Littérature citée [37 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-00779777
Contributeur : Marc Hoffmann <>
Soumis le : jeudi 24 janvier 2013 - 13:56:49
Dernière modification le : lundi 29 mai 2017 - 14:25:47
Document(s) archivé(s) le : jeudi 25 avril 2013 - 03:51:21

Fichier

euclid.ejs.1354284420.pdf
Fichiers éditeurs autorisés sur une archive ouverte

Identifiants

Collections

Citation

Sylvain Delattre, Marc Hoffmann, Dominique Picard, Thomas Vareschi. Blockwise SVD with error in the operator and application to blind deconvolution. Electronic journal of statistics , Shaker Heights, OH : Institute of Mathematical Statistics, 2012, 6, pp.2274-2308. 〈10.1214/12-EJS745〉. 〈hal-00779777〉

Partager

Métriques

Consultations de la notice

203

Téléchargements de fichiers

76