DocumentCode :
2805535
Title :
Coherence-based near-oracle performance guarantees for sparse estimation under Gaussian noise
Author :
Ben-Haim, Zvika ; Eldar, Yonina C. ; Elad, Michael
Author_Institution :
Technion - Israel Inst. of Technol., Haifa, Israel
fYear :
2010
fDate :
14-19 March 2010
Firstpage :
3590
Lastpage :
3593
Abstract :
We consider the problem of estimating a deterministic sparse vector x0 from underdetermined measurements Ax0 + 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, orthogonal matching pursuit, and thresholding. These approaches are shown to achieve near-oracle performance with high probability, assuming that x0 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.
Keywords :
Gaussian noise; estimation theory; Gaussian noise; basis pursuit denoising; coherence-based near-oracle performance guarantees; deterministic dictionary; deterministic sparse vector; orthogonal matching pursuit; sparse estimation; Algorithm design and analysis; Dictionaries; Gaussian noise; Greedy algorithms; Matching pursuit algorithms; Noise measurement; Noise reduction; Performance analysis; Pursuit algorithms; Wireless communication; Sparse estimation; basis pursuit; matching pursuit; oracle; thresholding algorithm;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Acoustics Speech and Signal Processing (ICASSP), 2010 IEEE International Conference on
Conference_Location :
Dallas, TX
ISSN :
1520-6149
Print_ISBN :
978-1-4244-4295-9
Electronic_ISBN :
1520-6149
Type :
conf
DOI :
10.1109/ICASSP.2010.5495919
Filename :
5495919
Link To Document :
بازگشت