Anisotropic oracle inequalities in noisy quantization

Abstract : The effect of errors in variables in quantization is investigated. We prove general exact and non-exact oracle inequalities with fast rates for an empirical minimization based on a noisy sample $Z_i=X_i+\epsilon_i,i=1,\ldots,n$, where $X_i$ are i.i.d. with density $f$ and $\epsilon_i$ are i.i.d. with density $\eta$. These rates depend on the geometry of the density $f$ and the asymptotic behaviour of the characteristic function of $\eta$. This general study can be applied to the problem of $k$-means clustering with noisy data. For this purpose, we introduce a deconvolution $k$-means stochastic minimization which reaches fast rates of convergence under standard Pollard's regularity assumptions.
Type de document :
Pré-publication, Document de travail
2013
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-00818307
Contributeur : Sébastien Loustau <>
Soumis le : vendredi 26 avril 2013 - 15:26:34
Dernière modification le : lundi 5 février 2018 - 15:00:03
Document(s) archivé(s) le : samedi 27 juillet 2013 - 04:20:08

Fichiers

aoinc.pdf
Fichiers éditeurs autorisés sur une archive ouverte

Identifiants

  • HAL Id : hal-00818307, version 1

Collections

Citation

Sébastien Loustau. Anisotropic oracle inequalities in noisy quantization. 2013. 〈hal-00818307〉

Partager

Métriques

Consultations de la notice

317

Téléchargements de fichiers

92