Convergence analysis of the LMS algorithm with a general error nonlinearity and an IID input

Tareq Y. Al-Naffouri; Azzedine Zerguine; Maamar Bettayeb

Convergence analysis of the LMS algorithm with a general error nonlinearity and an IID input

Tareq Y. Al-Naffouri^*, Azzedine Zerguine, Maamar Bettayeb

^*Corresponding author for this work

Research output: Contribution to journal › Conference article › peer-review

7 Scopus citations

Abstract

The class of least mean square (LMS) algorithms employing a general error nonlinearity is considered. A linearization approach is used to characterize the convergence and performance of this class of algorithms for an independent and identically distributed (iid) input. The analysis results are entirely consistent with those of the LMS algorithm and several of its variants. The results also encompass those of a recent work that considered the same class of algorithms for arbitrary and Gaussian inputs.

Original language	English (US)
Pages (from-to)	556-559
Number of pages	4
Journal	Conference Record of the Asilomar Conference on Signals, Systems and Computers
Volume	1
State	Published - 1998
Externally published	Yes
Event	Proceedings of the 1998 32nd Asilomar Conference on Signals, Systems & Computers. Part 1 (of 2) - Pacific Grove, CA, USA Duration: Nov 1 1998 → Nov 4 1998

ASJC Scopus subject areas

Signal Processing
Computer Networks and Communications

Cite this

@article{069c037f14914b1ba6c9a2a0ac93c9dc,

title = "Convergence analysis of the LMS algorithm with a general error nonlinearity and an IID input",

abstract = "The class of least mean square (LMS) algorithms employing a general error nonlinearity is considered. A linearization approach is used to characterize the convergence and performance of this class of algorithms for an independent and identically distributed (iid) input. The analysis results are entirely consistent with those of the LMS algorithm and several of its variants. The results also encompass those of a recent work that considered the same class of algorithms for arbitrary and Gaussian inputs.",

author = "Al-Naffouri, {Tareq Y.} and Azzedine Zerguine and Maamar Bettayeb",

year = "1998",

language = "English (US)",

volume = "1",

pages = "556--559",

journal = "Conference Record of the Asilomar Conference on Signals, Systems and Computers",

issn = "1058-6393",

publisher = "IEEE Computer Society",

note = "Proceedings of the 1998 32nd Asilomar Conference on Signals, Systems & Computers. Part 1 (of 2) ; Conference date: 01-11-1998 Through 04-11-1998",

}

TY - JOUR

T1 - Convergence analysis of the LMS algorithm with a general error nonlinearity and an IID input

AU - Al-Naffouri, Tareq Y.

AU - Zerguine, Azzedine

AU - Bettayeb, Maamar

PY - 1998

Y1 - 1998

N2 - The class of least mean square (LMS) algorithms employing a general error nonlinearity is considered. A linearization approach is used to characterize the convergence and performance of this class of algorithms for an independent and identically distributed (iid) input. The analysis results are entirely consistent with those of the LMS algorithm and several of its variants. The results also encompass those of a recent work that considered the same class of algorithms for arbitrary and Gaussian inputs.

AB - The class of least mean square (LMS) algorithms employing a general error nonlinearity is considered. A linearization approach is used to characterize the convergence and performance of this class of algorithms for an independent and identically distributed (iid) input. The analysis results are entirely consistent with those of the LMS algorithm and several of its variants. The results also encompass those of a recent work that considered the same class of algorithms for arbitrary and Gaussian inputs.

UR - http://www.scopus.com/inward/record.url?scp=0032260231&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:0032260231

SN - 1058-6393

VL - 1

SP - 556

EP - 559

JO - Conference Record of the Asilomar Conference on Signals, Systems and Computers

JF - Conference Record of the Asilomar Conference on Signals, Systems and Computers

T2 - Proceedings of the 1998 32nd Asilomar Conference on Signals, Systems & Computers. Part 1 (of 2)

Y2 - 1 November 1998 through 4 November 1998

ER -

Convergence analysis of the LMS algorithm with a general error nonlinearity and an IID input

Abstract

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this