Standard

SPSA With a Fixed Gain for Intelligent Control in Tracking Applications. / Granichin, O.; Gurevich, L.; Vakhitov, A.

2009 IEEE CONTROL APPLICATIONS CCA & INTELLIGENT CONTROL (ISIC), VOLS 1-3. IEEE Canada, 2009. стр. 1415-1420 (IEEE International Conference on Control Applications).

Результаты исследований: Публикации в книгах, отчётах, сборниках, трудах конференций › статья в сборнике материалов конференции › научная › Рецензирование

Harvard

Granichin, O, Gurevich, L & Vakhitov, A 2009, SPSA With a Fixed Gain for Intelligent Control in Tracking Applications. в 2009 IEEE CONTROL APPLICATIONS CCA & INTELLIGENT CONTROL (ISIC), VOLS 1-3. IEEE International Conference on Control Applications, IEEE Canada, стр. 1415-1420, IEEE International Conference on Control Applications/International Symposium on Intelligent Control, St Petersburg, 8/07/09. https://doi.org/10.1109/CCA.2009.5280941, https://doi.org/10.1109/CCA.2009.5280941

APA

Granichin, O., Gurevich, L., & Vakhitov, A. (2009). SPSA With a Fixed Gain for Intelligent Control in Tracking Applications. в 2009 IEEE CONTROL APPLICATIONS CCA & INTELLIGENT CONTROL (ISIC), VOLS 1-3 (стр. 1415-1420). (IEEE International Conference on Control Applications). IEEE Canada. https://doi.org/10.1109/CCA.2009.5280941, https://doi.org/10.1109/CCA.2009.5280941

Vancouver

Granichin O, Gurevich L, Vakhitov A. SPSA With a Fixed Gain for Intelligent Control in Tracking Applications. в 2009 IEEE CONTROL APPLICATIONS CCA & INTELLIGENT CONTROL (ISIC), VOLS 1-3. IEEE Canada. 2009. стр. 1415-1420. (IEEE International Conference on Control Applications). https://doi.org/10.1109/CCA.2009.5280941, https://doi.org/10.1109/CCA.2009.5280941

Author

Granichin, O. ; Gurevich, L. ; Vakhitov, A. / SPSA With a Fixed Gain for Intelligent Control in Tracking Applications. 2009 IEEE CONTROL APPLICATIONS CCA & INTELLIGENT CONTROL (ISIC), VOLS 1-3. IEEE Canada, 2009. стр. 1415-1420 (IEEE International Conference on Control Applications).

BibTeX

@inproceedings{02074650f9cf44ff961018e909cb19b0,
title = "SPSA With a Fixed Gain for Intelligent Control in Tracking Applications",
abstract = "Simultaneous perturbation stochastic approximation (SPSA) algorithm is also often referred as a Kiefer-Wolfowitz algorithm with randomized differences. Algorithms of this type are widely applied in field of intelligent control for optimization purposes, especially in a high-dimensional and noisy setting. In such problems it is often important to track the drifting minimum point, adapting to changing environment. In this paper application of the fixed gain SPSA to the minimum tracking problem for the non-constrained optimization is considered. The upper bound of mean square estimation error is determined in case of once differentiable functional and almost arbitrary noises. Numerical simulation of the estimates stabilization for the multidimensional optimization with non-random noise is provided.",
keywords = "STOCHASTIC-APPROXIMATION, ALGORITHM",
author = "O. Granichin and L. Gurevich and A. Vakhitov",
year = "2009",
doi = "10.1109/CCA.2009.5280941",
language = "Английский",
isbn = "978-1-4244-4601-8",
series = "IEEE International Conference on Control Applications",
publisher = "IEEE Canada",
pages = "1415--1420",
booktitle = "2009 IEEE CONTROL APPLICATIONS CCA & INTELLIGENT CONTROL (ISIC), VOLS 1-3",
address = "Канада",
note = "null ; Conference date: 08-07-2009 Through 10-07-2009",

}

RIS

TY - GEN

T1 - SPSA With a Fixed Gain for Intelligent Control in Tracking Applications

AU - Granichin, O.

AU - Gurevich, L.

AU - Vakhitov, A.

PY - 2009

Y1 - 2009

N2 - Simultaneous perturbation stochastic approximation (SPSA) algorithm is also often referred as a Kiefer-Wolfowitz algorithm with randomized differences. Algorithms of this type are widely applied in field of intelligent control for optimization purposes, especially in a high-dimensional and noisy setting. In such problems it is often important to track the drifting minimum point, adapting to changing environment. In this paper application of the fixed gain SPSA to the minimum tracking problem for the non-constrained optimization is considered. The upper bound of mean square estimation error is determined in case of once differentiable functional and almost arbitrary noises. Numerical simulation of the estimates stabilization for the multidimensional optimization with non-random noise is provided.

AB - Simultaneous perturbation stochastic approximation (SPSA) algorithm is also often referred as a Kiefer-Wolfowitz algorithm with randomized differences. Algorithms of this type are widely applied in field of intelligent control for optimization purposes, especially in a high-dimensional and noisy setting. In such problems it is often important to track the drifting minimum point, adapting to changing environment. In this paper application of the fixed gain SPSA to the minimum tracking problem for the non-constrained optimization is considered. The upper bound of mean square estimation error is determined in case of once differentiable functional and almost arbitrary noises. Numerical simulation of the estimates stabilization for the multidimensional optimization with non-random noise is provided.

KW - STOCHASTIC-APPROXIMATION

KW - ALGORITHM

U2 - 10.1109/CCA.2009.5280941

DO - 10.1109/CCA.2009.5280941

M3 - статья в сборнике материалов конференции

SN - 978-1-4244-4601-8

T3 - IEEE International Conference on Control Applications

SP - 1415

EP - 1420

BT - 2009 IEEE CONTROL APPLICATIONS CCA & INTELLIGENT CONTROL (ISIC), VOLS 1-3

PB - IEEE Canada

Y2 - 8 July 2009 through 10 July 2009

ER -

ID: 74014489