Structure-Blind Signal Recovery - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2016

Structure-Blind Signal Recovery


We consider the problem of recovering a signal observed in Gaussian noise. If the set of signals is convex and compact, and can be specified beforehand, one can use classical linear estimators that achieve a risk within a constant factor of the minimax risk. However, when the set is unspecified, designing an estimator that is blind to the hidden structure of the signal remains a challenging problem. We propose a new family of estimators to recover signals observed in Gaussian noise. Instead of specifying the set where the signal lives, we assume the existence of a well-performing linear estimator. Proposed estimators enjoy exact oracle inequalities and can be efficiently computed through convex optimization. We present several numerical illustrations that show the potential of the approach.
Fichier principal
Vignette du fichier
ohjn_structure-blind_recovery_hal_jul16.pdf (1.55 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-01345960 , version 1 (18-07-2016)


  • HAL Id : hal-01345960 , version 1


Dmitry Ostrovsky, Zaid Harchaoui, Anatoli B. Juditsky, Arkadi Nemirovski. Structure-Blind Signal Recovery. 30th International Conference on Neural Information Processing Systems - NIPS'16, Dec 2016, Barcelona, Spain. pp.4824-4832. ⟨hal-01345960⟩
178 View
33 Download


Gmail Facebook X LinkedIn More