Structure-Blind Signal Recovery

Abstract : 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.
Complete list of metadatas

Cited literature [21 references]  Display  Hide  Download

https://hal.inria.fr/hal-01345960
Contributor : Zaid Harchaoui <>
Submitted on : Monday, July 18, 2016 - 5:15:05 AM
Last modification on : Tuesday, June 18, 2019 - 3:14:07 PM

File

ohjn_structure-blind_recovery_...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01345960, version 1

Collections

Citation

Dmitry Ostrovsky, Zaid Harchaoui, Anatoli 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⟩

Share

Metrics

Record views

259

Files downloads

56