Abstract
The sufficient conditions are obtained for the convergence of the difference stochastic optimization procedure with impulse perturbations in a Markov environment under the conditions of exponential stability of the averaged system and smooth regression function of the source system. To this end, an asymptotic representation of the perturbed procedure generator is obtained.
Similar content being viewed by others
References
M. B. Nevelson and R. Z. Khasminskii, Stochastic Approximation and Recurrent Estimation [in Russian], Nauka, Moscow (1972).
L. Ljung, G. Pflug, and H. Walk, Stochastic Approximation and Optimization of Random Systems, Birkhauser Verlag, Basel–Boston–Berlin (1992).
Ya. Z. Tsypkin, Fundamentals of Learning Systems Theory [in Russian], Nauka, Moscow (1970).
A. V. Skorokhod, Asymptotic Methods of the Theory of Stochastic Differential Equations [in Russian], Naukova Dumka, Kyiv (1987).
V. Koroliuk and N. Limnios, Stochastic Systems in Merging Phase Space, World Sci. Publ., Singapore (2005).
S. A. Semenyuk and Ya. M. Chabanyuk, “Fluctuations of a stochastic system under an asymptotic diffusive perturbation,” Cybern. Syst. Analysis, 44, No. 5, 716–721 (2008).
V. S. Korolyuk and V. V. Korolyuk, Stochastic Models of Systems, Kluwer Acad. Publ., Dordrecht (1999).
Ya. M. Chabanyuk, “Continuous procedure of stochastic approximation with singular perturbation under balance conditions,” Cybern. Syst. Analysis, 42, No. 3, 420–425 (2006).
Author information
Authors and Affiliations
Corresponding author
Additional information
Translated from Kibernetika i Sistemnyi Analiz, No. 5, September–October, 2013, pp. 145–151.
Rights and permissions
About this article
Cite this article
Khimka, U.T., Chabanyuk, Y.M. A difference stochastic optimization procedure with impulse perturbation. Cybern Syst Anal 49, 768–773 (2013). https://doi.org/10.1007/s10559-013-9564-6
Received:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10559-013-9564-6