Adaptive Recovery of Signals by Convex Optimization - Archive ouverte HAL Access content directly
Conference Papers Year : 2015

Adaptive Recovery of Signals by Convex Optimization

(1, 2) , (3) , (4) , (3)
1
2
3
4

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.
Fichier principal
Vignette du fichier
hjno_colt15_hal.pdf (490.78 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

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

Identifiers

  • HAL Id : hal-01250215 , version 1

Cite

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⟩
319 View
208 Download

Share

Gmail Facebook Twitter LinkedIn More