Abstract
Consideration was given to the randomized stochastic approximation algorithm with simultaneous trial input perturbation and two measurements used to optimize the unconstrained nonstationary functional. The upper boundary of the mean-square residual was established under conditions of single differentiability of the functional and almost arbitrary noise. Efficiency of the algorithm was illustrated by an example of stabilization of the resulting estimates for the multidimensional case under dependent observation noise.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Popkov, A.Yu., Gradient Methods for Nonstationary Unconstrained Optimization Problems, Autom. Remote Control, 2005, no. 6, pp. 883–891.
Granichin, O.N. and Polyak, B.T., Randomizirovannye algoritmy otsenivaniya i optimizatsii pri pochti proizvol’nykh pomekhakh (Randomized Algorithms of Estimation and Optimization in almost Arbitrary Noise), Moscow: Nauka, 2003.
Polyak, B.T., Vvedenie v optimizatsiyu, Moscow: Nauka, 1983. Translated into English under the title Introduction to Optimization, New York: Optimization Software, 1987.
Kushner, H. and Yin, G., Stochastic Approximation and Recursive Algorithms and Applications, New York: Springer, 2003.
Granichin, O.N., Randomized Algorithms for Stochastic Approximation under Arbitrary Disturbances, Autom. Remote Control, 1992, no. 2, pp. 209–219.
Granichin, O.N., On a Recurrent Stochastic Procedure in Dependent Observation Noise Using Trail Input Perturbations, Vestn. Leningr. Gos. Univ., 1989, vol. 1, no. 1(4), pp. 19–21.
Polyak, B.T. and Tsybakov, A.B., Optimal Order of Precision of the Search Algorithms of Stochastic Approximation, Probl. Peredachi Inf., 1990, no. 26, pp. 126–133.
Spall, J.C., Multivariate Stochastic Approximation Using a Simultaneous Perturbation Gradient Approximation, IEEE Trans. Automat. Control, 1992, vol. 37, pp. 332–341.
Spall, J.C., Developments in Stochastic Optimization Algorithms with Gradient Approximations Based on Function Measurements, Proc. Winter Simulat. Conf., 1994, pp. 207–214.
Gurevich, L. and Vakhitov, A., SPSA Algorithm for Tracking, Proc. 12th Int. Student Olymp. Automat. Control (Baltic Olympiad), 2008, pp. 52–57.
Katkovnik, V.Ya. and Kheisin, V.E., Dynamic Stochastic Approximation of Polynomial Drifts, Autom. Remote Control, 1979, no. 5, pp. 700–708.
Author information
Authors and Affiliations
Additional information
Original Russian Text © A.T. Vakhitov, O.N. Granichin, L.S. Gurevich, 2009, published in Avtomatika i Telemekhanika, 2009, No. 11, pp. 70–79.
Rights and permissions
About this article
Cite this article
Vakhitov, A.T., Granichin, O.N. & Gurevich, L.S. Algorithm for stochastic approximation with trial input perturbation in the nonstationary problem of optimization. Autom Remote Control 70, 1827–1835 (2009). https://doi.org/10.1134/S000511790911006X
Received:
Published:
Issue Date:
DOI: https://doi.org/10.1134/S000511790911006X