Convergence rate determination for gradient-based adaptive estimators

Robert R. Bitmead; Brian D.O. Anderson; Tung Sang Ng

doi:10.1016/0005-1098(86)90079-8

Convergence rate determination for gradient-based adaptive estimators

Robert R. Bitmead^*, Brian D.O. Anderson, Tung Sang Ng

^*Corresponding author for this work

School of Engineering

Research output: Contribution to journal › Article › peer-review

13 Citations (Scopus)

Abstract

A convergence rate estimate is derived for the homogeneous gradient-based adaptive linear estimator algorithm. This estimate involves the eigenvalues of the regression vector covariance matrix, yielding a useful measure for the choice of input signals for adaptive parameter estimation. The connection between this criterion and those more familiar from nonadaptive system identification is made and comparisons are drawn between the two areas.

Original language	English
Pages (from-to)	185-191
Number of pages	7
Journal	Automatica
Volume	22
Issue number	2
DOIs	https://doi.org/10.1016/0005-1098(86)90079-8
Publication status	Published - Mar 1986

Access to Document

10.1016/0005-1098(86)90079-8

Cite this

@article{dfbfdd6b3a9a442397b4eb0067c5d8ea,

title = "Convergence rate determination for gradient-based adaptive estimators",

abstract = "A convergence rate estimate is derived for the homogeneous gradient-based adaptive linear estimator algorithm. This estimate involves the eigenvalues of the regression vector covariance matrix, yielding a useful measure for the choice of input signals for adaptive parameter estimation. The connection between this criterion and those more familiar from nonadaptive system identification is made and comparisons are drawn between the two areas.",

keywords = "Adaptive systems, averaging theory, convergence, parameter estimation, recursive algorithms, stochastic systems",

author = "Bitmead, {Robert R.} and Anderson, {Brian D.O.} and Ng, {Tung Sang}",

year = "1986",

month = mar,

doi = "10.1016/0005-1098(86)90079-8",

language = "English",

volume = "22",

pages = "185--191",

journal = "Automatica",

issn = "0005-1098",

publisher = "Elsevier Ltd.",

number = "2",

}

TY - JOUR

T1 - Convergence rate determination for gradient-based adaptive estimators

AU - Bitmead, Robert R.

AU - Anderson, Brian D.O.

AU - Ng, Tung Sang

PY - 1986/3

Y1 - 1986/3

N2 - A convergence rate estimate is derived for the homogeneous gradient-based adaptive linear estimator algorithm. This estimate involves the eigenvalues of the regression vector covariance matrix, yielding a useful measure for the choice of input signals for adaptive parameter estimation. The connection between this criterion and those more familiar from nonadaptive system identification is made and comparisons are drawn between the two areas.

AB - A convergence rate estimate is derived for the homogeneous gradient-based adaptive linear estimator algorithm. This estimate involves the eigenvalues of the regression vector covariance matrix, yielding a useful measure for the choice of input signals for adaptive parameter estimation. The connection between this criterion and those more familiar from nonadaptive system identification is made and comparisons are drawn between the two areas.

KW - Adaptive systems

KW - averaging theory

KW - convergence

KW - parameter estimation

KW - recursive algorithms

KW - stochastic systems

UR - http://www.scopus.com/inward/record.url?scp=0022681541&partnerID=8YFLogxK

U2 - 10.1016/0005-1098(86)90079-8

DO - 10.1016/0005-1098(86)90079-8

M3 - Article

AN - SCOPUS:0022681541

SN - 0005-1098

VL - 22

SP - 185

EP - 191

JO - Automatica

JF - Automatica

IS - 2

ER -

Convergence rate determination for gradient-based adaptive estimators

Abstract

Access to Document

Other files and links

Fingerprint

Cite this