Mathematics – Statistics Theory
Scientific paper
2011-11-10
Mathematics
Statistics Theory
Scientific paper
We discuss new methods for the recovery of signals with block-sparsestructure, based on $\ell_1$-minimization. Our emphasis is on verifiable conditions on the problem parameters (sensing matrix and the block structure) for accurate recovery and efficiently computable bounds for the recovery error. These bounds are then optimized with respect to the method parameters to construct the estimators with improved statisti- cal properties. To justify the proposed approach we provide an oracle inequality which links the properties of the recovery algorithms and the best estimation performance. We also propose a new matching pursuit algorithm for block-sparse recovery.
Juditsky Anatoli
Karzan Fatma Kilinc
Nemirovski Arkadi
Polyak Boris
No associations
LandOfFree
Accuracy guaranties for $\ell_1$ recovery of block-sparse signals does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Accuracy guaranties for $\ell_1$ recovery of block-sparse signals, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Accuracy guaranties for $\ell_1$ recovery of block-sparse signals will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-727999