Adaptive Recovery of Signals by Convex Optimization

Zaid Harchaoui 1, 2 Anatoli Juditsky 3 Arkadi Nemirovski 4, * Dmitry Ostrovsky 3
* Auteur correspondant
2 LEAR - Learning and recognition in vision
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
3 SMS - Statistique et Modélisation Stochatisque
LJK - Laboratoire Jean Kuntzmann
Abstract : 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.
Type de document :
Communication dans un congrès
JMLR Workshop and Conference Proceedings, Jul 2015, Paris, France. Proceedings of The 28th Conference on Learning Theory (40), pp.929-955, 2015, 〈http://www.learningtheory.org/colt2015/〉
Liste complète des métadonnées

Littérature citée [27 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01250215
Contributeur : <>
Soumis le : lundi 4 janvier 2016 - 14:41:55
Dernière modification le : lundi 11 septembre 2017 - 16:02:53
Document(s) archivé(s) le : vendredi 15 avril 2016 - 16:00:41

Fichier

hjno_colt15_hal.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01250215, version 1
  • Mot de passe : dxfu4uln

Citation

Zaid Harchaoui, Anatoli Juditsky, Arkadi Nemirovski, Dmitry Ostrovsky. Adaptive Recovery of Signals by Convex Optimization. JMLR Workshop and Conference Proceedings, Jul 2015, Paris, France. Proceedings of The 28th Conference on Learning Theory (40), pp.929-955, 2015, 〈http://www.learningtheory.org/colt2015/〉. 〈hal-01250215〉

Partager

Métriques

Consultations de la notice

428

Téléchargements de fichiers

168