COHERENCE-BASED NEAR-ORACLE PERFORMANCE GUARANTEES FOR SPARSE ESTIMATION UNDER GAUSSIAN NOISE

被引:3
作者
Ben-Haim, Zvika [1 ]
Eldar, Yonina C. [1 ]
Elad, Michael [1 ]
机构
[1] Technion Israel Inst Technol, IL-32000 Haifa, Israel
来源
2010 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING | 2010年
关键词
Sparse estimation; basis pursuit; matching pursuit; thresholding algorithm; oracle; DANTZIG SELECTOR;
D O I
10.1109/ICASSP.2010.5495919
中图分类号
O42 [声学];
学科分类号
070206 ; 082403 ;
摘要
We consider the problem of estimating a deterministic sparse vector x(0) from underdetermined measurements Ax(0) + 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 x(0) 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.
引用
收藏
页码:3590 / 3593
页数:4
相关论文
共 8 条
[1]  
BENHAIM Z, IEEE T SIGNAL UNPUB
[2]   SIMULTANEOUS ANALYSIS OF LASSO AND DANTZIG SELECTOR [J].
Bickel, Peter J. ;
Ritov, Ya'acov ;
Tsybakov, Alexandre B. .
ANNALS OF STATISTICS, 2009, 37 (04) :1705-1732
[3]  
CANDES EJ, 2006, ACTA NUMER, P1
[4]  
Candes E, 2007, ANN STAT, V35, P2313, DOI 10.1214/009053606000001523
[5]   NEAR-IDEAL MODEL SELECTION BY l1 MINIMIZATION [J].
Candes, Emmanuel J. ;
Plan, Yaniv .
ANNALS OF STATISTICS, 2009, 37 (5A) :2145-2177
[6]   Atomic decomposition by basis pursuit [J].
Chen, SSB ;
Donoho, DL ;
Saunders, MA .
SIAM JOURNAL ON SCIENTIFIC COMPUTING, 1998, 20 (01) :33-61
[7]   Stable recovery of sparse overcomplete representations in the presence of noise [J].
Donoho, DL ;
Elad, M ;
Temlyakov, VN .
IEEE TRANSACTIONS ON INFORMATION THEORY, 2006, 52 (01) :6-18
[8]  
PATI YC, 1993, P 27 AS C SIGN SYST, P40, DOI DOI 10.1109/ACSSC.1993.342465