Open Access
Translator Disclaimer
September, 1973 Extensions of Kesten's Adaptive Stochastic Approximation Method
H. J. Kushner, T. Gavin
Ann. Statist. 1(5): 851-861 (September, 1973). DOI: 10.1214/aos/1176342506


Kesten proposed a method for adjusting the coefficients of a scalar stochastic approximation process, and proved w.p. 1 convergence. A family of multidimensional processes for function minimization are treated here. Each method consists of a sequence of truncated one-dimensional procedures of the Kesten type. The methods seem to offer a number of advantages over the usual Kiefer-Wolfowitz procedures, and are more natural analogs of the schemes in common use in deterministic optimization theory.


Download Citation

H. J. Kushner. T. Gavin. "Extensions of Kesten's Adaptive Stochastic Approximation Method." Ann. Statist. 1 (5) 851 - 861, September, 1973.


Published: September, 1973
First available in Project Euclid: 12 April 2007

zbMATH: 0285.62054
MathSciNet: MR378305
Digital Object Identifier: 10.1214/aos/1176342506

Keywords: adaptive process , Monte-carlo , sequential analysis , sequential optimization with noisy observations , stochastic approximation

Rights: Copyright © 1973 Institute of Mathematical Statistics


Vol.1 • No. 5 • September, 1973
Back to Top