A Stability Analysis of the Modified NLMS Rules
A Stability Analysis of the Modified NLMS Rules
This paper investigates the stability of two recently proposed modified NLMS learning rules that are based on calculating the smallest weight change which stores the current training pattern exactly. The Lp (p = 1, 2, infinity) norm used to measure the weight update produces different learning algorithms, and it is shown that both new learning rules (p = 1, infinity) can become unstable, as the parameter error increases without bound. This is in direct contrast to the standard (p = 2 norm) NLMS rule which is unconditionally stable (in the sense described in this paper - monotonically non-increasing weight error), and indeed the NLMS rule was originally derived to overcome such limitations. The conditions under which instability can occur are investigated both theoretically and in simulation and are shown to depend on the form of the input vector and only indirectly on the learning rate.
Brown, M.
52cf4f52-6839-4658-8cc5-ec51da626049
An, P.E.
5dc94657-d009-4d13-9a0f-6645a9d296d9
Harris, C.J.
c4fd3763-7b3f-4db1-9ca3-5501080f797a
1995
Brown, M.
52cf4f52-6839-4658-8cc5-ec51da626049
An, P.E.
5dc94657-d009-4d13-9a0f-6645a9d296d9
Harris, C.J.
c4fd3763-7b3f-4db1-9ca3-5501080f797a
Brown, M., An, P.E. and Harris, C.J.
(1995)
A Stability Analysis of the Modified NLMS Rules.
IEEE Trans. on Signal Processing.
Abstract
This paper investigates the stability of two recently proposed modified NLMS learning rules that are based on calculating the smallest weight change which stores the current training pattern exactly. The Lp (p = 1, 2, infinity) norm used to measure the weight update produces different learning algorithms, and it is shown that both new learning rules (p = 1, infinity) can become unstable, as the parameter error increases without bound. This is in direct contrast to the standard (p = 2 norm) NLMS rule which is unconditionally stable (in the sense described in this paper - monotonically non-increasing weight error), and indeed the NLMS rule was originally derived to overcome such limitations. The conditions under which instability can occur are investigated both theoretically and in simulation and are shown to depend on the form of the input vector and only indirectly on the learning rate.
This record has no associated files available for download.
More information
Published date: 1995
Additional Information:
submitted for publication
Organisations:
Southampton Wireless Group
Identifiers
Local EPrints ID: 250283
URI: http://eprints.soton.ac.uk/id/eprint/250283
PURE UUID: 01846b74-f438-45f4-8df9-3c5d2530cfc0
Catalogue record
Date deposited: 04 May 1999
Last modified: 10 Dec 2021 20:07
Export record
Contributors
Author:
M. Brown
Author:
P.E. An
Author:
C.J. Harris
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics