Standard

SPSA-based adaptive control : Accuracy of estimates. / Vakhitov, Alexander T.; Granichin, Oleg N.

9th IFAC Workshop "Adaptation and Learning in Control and Signal Processing", ALCOSP'2007 - Final Program and Abstracts. Vol. 9 PART 1. ed. 2007. p. 429-434.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Research › peer-review

Harvard

Vakhitov, AT & Granichin, ON 2007, SPSA-based adaptive control: Accuracy of estimates. in 9th IFAC Workshop "Adaptation and Learning in Control and Signal Processing", ALCOSP'2007 - Final Program and Abstracts. PART 1 edn, vol. 9, pp. 429-434, 9th IFAC Workshop "Adaptation and Learning in Control and Signal Processing", Saint Petersburg, Russian Federation, 29/08/07.

APA

Vakhitov, A. T., & Granichin, O. N. (2007). SPSA-based adaptive control: Accuracy of estimates. In 9th IFAC Workshop "Adaptation and Learning in Control and Signal Processing", ALCOSP'2007 - Final Program and Abstracts (PART 1 ed., Vol. 9, pp. 429-434)

Vancouver

Vakhitov AT, Granichin ON. SPSA-based adaptive control: Accuracy of estimates. In 9th IFAC Workshop "Adaptation and Learning in Control and Signal Processing", ALCOSP'2007 - Final Program and Abstracts. PART 1 ed. Vol. 9. 2007. p. 429-434

Author

Vakhitov, Alexander T. ; Granichin, Oleg N. / SPSA-based adaptive control : Accuracy of estimates. 9th IFAC Workshop "Adaptation and Learning in Control and Signal Processing", ALCOSP'2007 - Final Program and Abstracts. Vol. 9 PART 1. ed. 2007. pp. 429-434

BibTeX

@inproceedings{25c62370a2c14a67882b1842c92c9f84,
title = "SPSA-based adaptive control: Accuracy of estimates",
abstract = "Accuracy for main class of Simultaneous Perturbation Stochastic Approximation (SPSA) procedures is being researched. The model of observation is considered to be one of the most general among SPSA research. The power of moments of expectation for which the estimates of the procedure do converge is lowerized from 2 to 1 (not including lower bound). The conditions for the convergence are presented, with additional generalisations made about heavy-tailed noise and trial perturbation properties.",
keywords = "Intelligent control, Learning control, Nonlinear control, Stochastic systems",
author = "Vakhitov, {Alexander T.} and Granichin, {Oleg N.}",
year = "2007",
month = dec,
day = "1",
language = "English",
isbn = "9783902661296",
volume = "9",
pages = "429--434",
booktitle = "9th IFAC Workshop {"}Adaptation and Learning in Control and Signal Processing{"}, ALCOSP'2007 - Final Program and Abstracts",
edition = "PART 1",
note = "9th IFAC Workshop {"}Adaptation and Learning in Control and Signal Processing{"}, ALCOSP'2007 ; Conference date: 29-08-2007 Through 31-08-2007",

}

RIS

TY - GEN

T1 - SPSA-based adaptive control

T2 - 9th IFAC Workshop "Adaptation and Learning in Control and Signal Processing"

AU - Vakhitov, Alexander T.

AU - Granichin, Oleg N.

PY - 2007/12/1

Y1 - 2007/12/1

N2 - Accuracy for main class of Simultaneous Perturbation Stochastic Approximation (SPSA) procedures is being researched. The model of observation is considered to be one of the most general among SPSA research. The power of moments of expectation for which the estimates of the procedure do converge is lowerized from 2 to 1 (not including lower bound). The conditions for the convergence are presented, with additional generalisations made about heavy-tailed noise and trial perturbation properties.

AB - Accuracy for main class of Simultaneous Perturbation Stochastic Approximation (SPSA) procedures is being researched. The model of observation is considered to be one of the most general among SPSA research. The power of moments of expectation for which the estimates of the procedure do converge is lowerized from 2 to 1 (not including lower bound). The conditions for the convergence are presented, with additional generalisations made about heavy-tailed noise and trial perturbation properties.

KW - Intelligent control

KW - Learning control

KW - Nonlinear control

KW - Stochastic systems

UR - http://www.scopus.com/inward/record.url?scp=79961085115&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:79961085115

SN - 9783902661296

VL - 9

SP - 429

EP - 434

BT - 9th IFAC Workshop "Adaptation and Learning in Control and Signal Processing", ALCOSP'2007 - Final Program and Abstracts

Y2 - 29 August 2007 through 31 August 2007

ER -

ID: 32480394