This paper provides a novel normalized sign least-mean square (NSLMS) algorithm which updates only a part of the filter coefficients and simultaneously performs sparse updates with the goal of reducing computational complexity. A combination of the partial-update scheme and the set-membership framework is incorporated into the context of L∞-norm adaptive filtering, thus yielding computational efficiency. For the stabilized convergence, we formulate a robust update recursion by imposing an upper bound of a step size. Furthermore, we analyzed a mean-square stability of the proposed algorithm for white input signals. Experimental results show that the proposed low-complexity NSLMS algorithm has similar convergence performance with greatly reduced computational complexity compared to the partial-update NSLMS, and is comparable to the set-membership partial-update NLMS.
Seong-Eun KIM
Samsung Electronics
Young-Seok CHOI
Gangneung-Wonju National University
Jae-Woo LEE
Pohang University of Science and Technology (POSTECH)
Woo-Jin SONG
Pohang University of Science and Technology (POSTECH)
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Seong-Eun KIM, Young-Seok CHOI, Jae-Woo LEE, Woo-Jin SONG, "Partial-Update Normalized Sign LMS Algorithm Employing Sparse Updates" in IEICE TRANSACTIONS on Fundamentals,
vol. E96-A, no. 6, pp. 1482-1487, June 2013, doi: 10.1587/transfun.E96.A.1482.
Abstract: This paper provides a novel normalized sign least-mean square (NSLMS) algorithm which updates only a part of the filter coefficients and simultaneously performs sparse updates with the goal of reducing computational complexity. A combination of the partial-update scheme and the set-membership framework is incorporated into the context of L∞-norm adaptive filtering, thus yielding computational efficiency. For the stabilized convergence, we formulate a robust update recursion by imposing an upper bound of a step size. Furthermore, we analyzed a mean-square stability of the proposed algorithm for white input signals. Experimental results show that the proposed low-complexity NSLMS algorithm has similar convergence performance with greatly reduced computational complexity compared to the partial-update NSLMS, and is comparable to the set-membership partial-update NLMS.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.E96.A.1482/_p
Copy
@ARTICLE{e96-a_6_1482,
author={Seong-Eun KIM, Young-Seok CHOI, Jae-Woo LEE, Woo-Jin SONG, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Partial-Update Normalized Sign LMS Algorithm Employing Sparse Updates},
year={2013},
volume={E96-A},
number={6},
pages={1482-1487},
abstract={This paper provides a novel normalized sign least-mean square (NSLMS) algorithm which updates only a part of the filter coefficients and simultaneously performs sparse updates with the goal of reducing computational complexity. A combination of the partial-update scheme and the set-membership framework is incorporated into the context of L∞-norm adaptive filtering, thus yielding computational efficiency. For the stabilized convergence, we formulate a robust update recursion by imposing an upper bound of a step size. Furthermore, we analyzed a mean-square stability of the proposed algorithm for white input signals. Experimental results show that the proposed low-complexity NSLMS algorithm has similar convergence performance with greatly reduced computational complexity compared to the partial-update NSLMS, and is comparable to the set-membership partial-update NLMS.},
keywords={},
doi={10.1587/transfun.E96.A.1482},
ISSN={1745-1337},
month={June},}
Copy
TY - JOUR
TI - Partial-Update Normalized Sign LMS Algorithm Employing Sparse Updates
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 1482
EP - 1487
AU - Seong-Eun KIM
AU - Young-Seok CHOI
AU - Jae-Woo LEE
AU - Woo-Jin SONG
PY - 2013
DO - 10.1587/transfun.E96.A.1482
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E96-A
IS - 6
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - June 2013
AB - This paper provides a novel normalized sign least-mean square (NSLMS) algorithm which updates only a part of the filter coefficients and simultaneously performs sparse updates with the goal of reducing computational complexity. A combination of the partial-update scheme and the set-membership framework is incorporated into the context of L∞-norm adaptive filtering, thus yielding computational efficiency. For the stabilized convergence, we formulate a robust update recursion by imposing an upper bound of a step size. Furthermore, we analyzed a mean-square stability of the proposed algorithm for white input signals. Experimental results show that the proposed low-complexity NSLMS algorithm has similar convergence performance with greatly reduced computational complexity compared to the partial-update NSLMS, and is comparable to the set-membership partial-update NLMS.
ER -