Abstract
Consideration was given to the Robbins–Monro procedure for which the Dvoretzky theorem of its convergence rate was generalized. The rate of convergence is still the most important problem of the theory of stochastic approximation.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Granichin, O.N. and Polyak, B.T., Randomizirovannye algoritmy otsenivaniya i optimizatsii pri pochti proizvol’nykh pomekhakh (Randomized Algorithms of Estimation and Optimization for Almost Arbitrary Noise), Moscow: Nauka, 2003.
Kushner, H.J. and Yin, G.G., Stochastic Approximation Algorithms and Applications, New York: Springer, 1997.
Dvoretzky, A., On Stochastic Approximation, in Proc. 3 Berkeley Symp. Mathematical Statistics Probability, 1956, vol. 1, pp. 39–55.
Author information
Authors and Affiliations
Corresponding author
Additional information
Original Russian Text © T.P. Krasulina, 2016, published in Avtomatika i Telemekhanika, 2016, No. 8, pp. 101–104.
Rights and permissions
About this article
Cite this article
Krasulina, T.P. Generalization of the Dvoretzky theorem of convergence rate of the stochastic approximation algorithms. Autom Remote Control 77, 1399–1402 (2016). https://doi.org/10.1134/S0005117916080063
Received:
Published:
Issue Date:
DOI: https://doi.org/10.1134/S0005117916080063