A stochastic approximation procedure with a singularly perturbed regression function is considered. The form of the limit process is obtained that corresponds to the fluctuation of the stochastic approximation procedure in the neighborhood of an equilibrium point. A generator for the limit process is also constructed. The solution of the singular perturbation problem is given for the asymptotic representation of the generator of a Markov renewal process. The results obtained allow one to extend the possibilities of investigation of the asymptotic behavior of the procedure itself.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
M. B. Nevelson and R. Z. Hasminskii, Stochastic Approximation and Recurrent Estimation [in Russian], Nauka, Moscow (1972).
Ya. M. Chabanyuk, “Continuous procedure of stochastic approximation with singular perturbation under balance conditions,” Cybernetics and Systems Analysis, No. 3, 420–425 (2006).
L. Ljung, G. Pflung, and H. Walk, Stochastic Approximation and Optimization of Random Systems, Birkhauser, Basel (1992).
V. S. Korolyuk and N. Limnius, Stochastic Systems in Merging Phase Space, World Scientific, Dordrecht (2005).
Author information
Authors and Affiliations
Corresponding author
Additional information
Translated from Kibernetika i Sistemnyi Analiz, No. 5, pp. 175–179, September–October 2009.
Rights and permissions
About this article
Cite this article
Semenyuk, S.A. Fluctuations of a stochastic approximation procedure with diffusion perturbation. Cybern Syst Anal 45, 829–834 (2009). https://doi.org/10.1007/s10559-009-9144-y
Received:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10559-009-9144-y