Paper Info
Title
Lorentzian based iterative hard thresholding for compressed sensing.
Abstract
In this paper we propose a robust iterative hard thresholding (IHT) algorithm for reconstructing sparse signals in the presence of impulsive noise. To address this problem, we use a Lorentzian cost function instead of the L2 cost function employed by the traditional IHT algorithm. The derived algorithm is comparable in computational load to the least squares based IHT. Analysis of the proposed method demonstrates its robustness under heavy-tailed models. Simulations show that the proposed algorithm significantly outperform commonly employed sparse reconstruction techniques in impulsive environments, while providing comparable reconstruction quality in less demanding, light-tailed environments.
Year
DOI
Venue
2011
10.1109/ICASSP.2011.5947145
ICASSP
Keywords
Field
DocType
impulse noise,cost function,heavy tail,least square,compressed sensing
Least squares,Mathematical optimization,Pattern recognition,Computer science,Robustness (computer science),Artificial intelligence,Impulse noise,Thresholding,Compressed sensing
Conference
ISSN
ISBN
Citations 
1520-6149 E-ISBN : 978-1-4577-0537-3
978-1-4577-0537-3
8
PageRank 
References 
Authors
0.59
6
2
Name
Order
Citations
PageRank
Rafael E. Carrillo125015.90
Kenneth E. Barner281270.19