Mathematics – Statistics Theory
Scientific paper
2009-03-26
Mathematics
Statistics Theory
12 pages, 3 figures. Submitted to IEEE Transactions on Signal Processing
Scientific paper
We consider the problem of estimating a deterministic sparse vector x from underdetermined measurements Ax+w, where w represents white Gaussian noise and A is a given deterministic dictionary. We analyze the performance of three sparse estimation algorithms: basis pursuit denoising (BPDN), orthogonal matching pursuit (OMP), and thresholding. These algorithms are shown to achieve near-oracle performance with high probability, assuming that x is sufficiently sparse. Our results are non-asymptotic and are based only on the coherence of A, so that they are applicable to arbitrary dictionaries. Differences in the precise conditions required for the performance guarantees of each algorithm are manifested in the observed performance at high and low signal-to-noise ratios. This provides insight on the advantages and drawbacks of convex relaxation techniques such as BPDN as opposed to greedy approaches such as OMP and thresholding.
Ben-Haim Zvika
Elad Michael
Eldar Yonina C.
No associations
LandOfFree
Coherence-Based Performance Guarantees for Estimating a Sparse Vector Under Random Noise 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 Coherence-Based Performance Guarantees for Estimating a Sparse Vector Under Random Noise, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Coherence-Based Performance Guarantees for Estimating a Sparse Vector Under Random Noise will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-64773