Adaptive Recovery of Signals by Convex Optimization - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2015

Adaptive Recovery of Signals by Convex Optimization

Résumé

We present a theoretical framework for adaptive estimation and prediction of signals of unknown structure in the presence of noise. The framework allows to address two intertwined challenges: (i) designing optimal statistical estimators; (ii) designing efficient numerical algorithms. In particular, we establish oracle inequalities for the performance of adaptive procedures, which rely upon convex optimization and thus can be efficiently implemented. As an application of the proposed approach, we consider denoising of harmonic oscillations.
Fichier principal
Vignette du fichier
hjno_colt15_hal.pdf (490.78 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01250215 , version 1 (04-01-2016)

Identifiants

  • HAL Id : hal-01250215 , version 1

Citer

Zaid Harchaoui, Anatoli B. Juditsky, Arkadi Nemirovski, Dmitry Ostrovsky. Adaptive Recovery of Signals by Convex Optimization. JMLR Workshop and Conference Proceedings, Jul 2015, Paris, France. pp.929-955. ⟨hal-01250215⟩
423 Consultations
229 Téléchargements

Partager

Gmail Facebook X LinkedIn More