Timezone: »

Structure-Blind Signal Recovery
Dmitry Ostrovsky · Zaid Harchaoui · Anatoli Juditsky · Arkadi S Nemirovski

Wed Dec 07 09:00 AM -- 12:30 PM (PST) @ Area 5+6+7+8 #47

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.

Author Information

Dmitry Ostrovsky (Univ. Grenoble Alpes)
Zaid Harchaoui (NYU)
Anatoli Juditsky (UJF)
Arkadi S Nemirovski (Gerogia Institute of Technology)

More from the Same Authors