Almost sure convergence of the normed LMS algorithm with error feedback delay

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In some applications of LMS type adaptive algorithms, it is necessary to implement a variant of the algorithm with feedback delay in the weight update calculation. In this paper we consider the normed version of such an algorithm and show that the algorithm converges exponentially if the update gain parameter, μm, is sufficiently small. The result is first proved for inputs which satisfy a standard deterministic mixing condition, and then the development is extended to the case when the input may not be strictly mixing, but is instead a stationary ergodic vector sequence with positive definite autocorrelation.

Original languageEnglish (US)
Title of host publicationConference Record of the Asilomar Conference on Signals, Systems & Computers
EditorsAvtar Singh
PublisherPubl by IEEE
Pages179-183
Number of pages5
Volume1
ISBN (Print)0818641207
StatePublished - 1993
EventProceedings of the 27th Asilomar Conference on Signals, Systems & Computers - Pacific Grove, CA, USA
Duration: Nov 1 1993Nov 3 1993

Other

OtherProceedings of the 27th Asilomar Conference on Signals, Systems & Computers
CityPacific Grove, CA, USA
Period11/1/9311/3/93

Fingerprint

Feedback
Adaptive algorithms
Autocorrelation

ASJC Scopus subject areas

  • Hardware and Architecture
  • Signal Processing
  • Electrical and Electronic Engineering

Cite this

Voltz, P. (1993). Almost sure convergence of the normed LMS algorithm with error feedback delay. In A. Singh (Ed.), Conference Record of the Asilomar Conference on Signals, Systems & Computers (Vol. 1, pp. 179-183). Publ by IEEE.

Almost sure convergence of the normed LMS algorithm with error feedback delay. / Voltz, Peter.

Conference Record of the Asilomar Conference on Signals, Systems & Computers. ed. / Avtar Singh. Vol. 1 Publ by IEEE, 1993. p. 179-183.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Voltz, P 1993, Almost sure convergence of the normed LMS algorithm with error feedback delay. in A Singh (ed.), Conference Record of the Asilomar Conference on Signals, Systems & Computers. vol. 1, Publ by IEEE, pp. 179-183, Proceedings of the 27th Asilomar Conference on Signals, Systems & Computers, Pacific Grove, CA, USA, 11/1/93.
Voltz P. Almost sure convergence of the normed LMS algorithm with error feedback delay. In Singh A, editor, Conference Record of the Asilomar Conference on Signals, Systems & Computers. Vol. 1. Publ by IEEE. 1993. p. 179-183
Voltz, Peter. / Almost sure convergence of the normed LMS algorithm with error feedback delay. Conference Record of the Asilomar Conference on Signals, Systems & Computers. editor / Avtar Singh. Vol. 1 Publ by IEEE, 1993. pp. 179-183
@inproceedings{969f5c8c859c44f3852cfb614a00db93,
title = "Almost sure convergence of the normed LMS algorithm with error feedback delay",
abstract = "In some applications of LMS type adaptive algorithms, it is necessary to implement a variant of the algorithm with feedback delay in the weight update calculation. In this paper we consider the normed version of such an algorithm and show that the algorithm converges exponentially if the update gain parameter, μm, is sufficiently small. The result is first proved for inputs which satisfy a standard deterministic mixing condition, and then the development is extended to the case when the input may not be strictly mixing, but is instead a stationary ergodic vector sequence with positive definite autocorrelation.",
author = "Peter Voltz",
year = "1993",
language = "English (US)",
isbn = "0818641207",
volume = "1",
pages = "179--183",
editor = "Avtar Singh",
booktitle = "Conference Record of the Asilomar Conference on Signals, Systems & Computers",
publisher = "Publ by IEEE",

}

TY - GEN

T1 - Almost sure convergence of the normed LMS algorithm with error feedback delay

AU - Voltz, Peter

PY - 1993

Y1 - 1993

N2 - In some applications of LMS type adaptive algorithms, it is necessary to implement a variant of the algorithm with feedback delay in the weight update calculation. In this paper we consider the normed version of such an algorithm and show that the algorithm converges exponentially if the update gain parameter, μm, is sufficiently small. The result is first proved for inputs which satisfy a standard deterministic mixing condition, and then the development is extended to the case when the input may not be strictly mixing, but is instead a stationary ergodic vector sequence with positive definite autocorrelation.

AB - In some applications of LMS type adaptive algorithms, it is necessary to implement a variant of the algorithm with feedback delay in the weight update calculation. In this paper we consider the normed version of such an algorithm and show that the algorithm converges exponentially if the update gain parameter, μm, is sufficiently small. The result is first proved for inputs which satisfy a standard deterministic mixing condition, and then the development is extended to the case when the input may not be strictly mixing, but is instead a stationary ergodic vector sequence with positive definite autocorrelation.

UR - http://www.scopus.com/inward/record.url?scp=0027814135&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0027814135&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0027814135

SN - 0818641207

VL - 1

SP - 179

EP - 183

BT - Conference Record of the Asilomar Conference on Signals, Systems & Computers

A2 - Singh, Avtar

PB - Publ by IEEE

ER -