Skip to main content

Comparison of SPARLS and RLS algorithms for adaptive filtering

Publication ,  Conference
Babadi, B; Kalouptsidis, N; Tarokh, V
Published in: 2009 IEEE Sarnoff Symposium Sarnoff 2009 Conference Proceedings
July 23, 2009

In this paper, we overview the Low Complexity Recursive ℒ1-Regularized Least Squares (SPARLS) algorithm proposed in [2], for the estimation of sparse signals in an adaptive filtering setting. The SPARLS algorithm is based on an Expectation-Maximization type algorithm adapted for online estimation. Simulation results for the estimation of multi-path wireless channels show that the SPARLS algorithm has significant improvement over the conventional widely-used Recursive Least Squares (RLS) algorithm, in terms of both mean squared error (MSE) and computational complexity.

Duke Scholars

Published In

2009 IEEE Sarnoff Symposium Sarnoff 2009 Conference Proceedings

DOI

Publication Date

July 23, 2009
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Babadi, B., Kalouptsidis, N., & Tarokh, V. (2009). Comparison of SPARLS and RLS algorithms for adaptive filtering. In 2009 IEEE Sarnoff Symposium Sarnoff 2009 Conference Proceedings. https://doi.org/10.1109/SARNOF.2009.4850336
Babadi, B., N. Kalouptsidis, and V. Tarokh. “Comparison of SPARLS and RLS algorithms for adaptive filtering.” In 2009 IEEE Sarnoff Symposium Sarnoff 2009 Conference Proceedings, 2009. https://doi.org/10.1109/SARNOF.2009.4850336.
Babadi B, Kalouptsidis N, Tarokh V. Comparison of SPARLS and RLS algorithms for adaptive filtering. In: 2009 IEEE Sarnoff Symposium Sarnoff 2009 Conference Proceedings. 2009.
Babadi, B., et al. “Comparison of SPARLS and RLS algorithms for adaptive filtering.” 2009 IEEE Sarnoff Symposium Sarnoff 2009 Conference Proceedings, 2009. Scopus, doi:10.1109/SARNOF.2009.4850336.
Babadi B, Kalouptsidis N, Tarokh V. Comparison of SPARLS and RLS algorithms for adaptive filtering. 2009 IEEE Sarnoff Symposium Sarnoff 2009 Conference Proceedings. 2009.

Published In

2009 IEEE Sarnoff Symposium Sarnoff 2009 Conference Proceedings

DOI

Publication Date

July 23, 2009