Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

Feature LMS Algorithms

Abstract: 

In recent years, there is a growing effort in the learning algorithms area to propose new strategies to detect and exploit sparsity in the model parameters. In many situations, the sparsity is hidden in the relations among these coefficients so that some suitable tools are required to reveal the potential sparsity. This work proposes a set of LMS-type algorithms, collectively called Feature LMS (F-LMS) algorithms, setting forth a hidden feature of the unknown parameters, which ultimately would improve convergence speed and steady-state mean-squared error. The key idea is to apply linear transformations, by means of the so-called feature matrices, to reveal the sparsity hidden in the coefficient vector, followed by a sparsity-promoting penalty function to exploit such sparsity. Some F-LMS algorithms for lowpass and highpass systems are also introduced by using simple feature matrices that require only trivial operations. Simulation results demonstrate that the proposed F-LMS algorithms bring about several performance
improvements whenever the hidden sparsity of the parameters is exposed.

up
1 user has voted: Paulo Diniz

Paper Details

Authors:
Paulo Sergio Ramirez Diniz, Hamed Yazdanpanah, Markus Vinicius Santos Lima
Submitted On:
14 April 2018 - 11:53pm
Short Link:
Type:
Presentation Slides
Event:
Presenter's Name:
Paulo Sergio Ramirez Diniz
Paper Code:
3575
Document Year:
2018
Cite

Document Files

ICASSP2018_Diniz_Presentation.pdf

(130)

Subscribe

[1] Paulo Sergio Ramirez Diniz, Hamed Yazdanpanah, Markus Vinicius Santos Lima, "Feature LMS Algorithms", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2874. Accessed: Aug. 17, 2019.
@article{2874-18,
url = {http://sigport.org/2874},
author = {Paulo Sergio Ramirez Diniz; Hamed Yazdanpanah; Markus Vinicius Santos Lima },
publisher = {IEEE SigPort},
title = {Feature LMS Algorithms},
year = {2018} }
TY - EJOUR
T1 - Feature LMS Algorithms
AU - Paulo Sergio Ramirez Diniz; Hamed Yazdanpanah; Markus Vinicius Santos Lima
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2874
ER -
Paulo Sergio Ramirez Diniz, Hamed Yazdanpanah, Markus Vinicius Santos Lima. (2018). Feature LMS Algorithms. IEEE SigPort. http://sigport.org/2874
Paulo Sergio Ramirez Diniz, Hamed Yazdanpanah, Markus Vinicius Santos Lima, 2018. Feature LMS Algorithms. Available at: http://sigport.org/2874.
Paulo Sergio Ramirez Diniz, Hamed Yazdanpanah, Markus Vinicius Santos Lima. (2018). "Feature LMS Algorithms." Web.
1. Paulo Sergio Ramirez Diniz, Hamed Yazdanpanah, Markus Vinicius Santos Lima. Feature LMS Algorithms [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2874