On the almost sure convergence of a general stochastic approximation procedure
- 1 December 1986
- journal article
- research article
- Published by Cambridge University Press (CUP) in Bulletin of the Australian Mathematical Society
- Vol. 34 (3), 335-342
- https://doi.org/10.1017/s0004972700010236
Abstract
A set of conditions for the almost sure convergence of a stochastic iterative procedure is given. The conditions are framed in terms of the behaviour of the random adjustment made the n-th step rather than in terms of some underlying regression model.Keywords
This publication has 12 references indexed in Scilit:
- Stochastic approximation with dependent noiseStochastic Processes and their Applications, 1982
- Almost Sure Approximations to the Robbins-Monro and Kiefer-Wolfowitz Processes with Dependent NoiseThe Annals of Probability, 1982
- Almost Sure Convergence for the Robbins-Monro ProcessThe Annals of Probability, 1976
- Inequalities for the $r$th Absolute Moment of a Sum of Random Variables, $1 \leqq r \leqq 2$The Annals of Mathematical Statistics, 1965
- On Stochastic ApproximationsThe Annals of Mathematical Statistics, 1963
- ON STOCHASTIC APPROXIMATIONPublished by University of California Press ,1956
- On a Class of Stochastic Approximation ProcessesThe Annals of Mathematical Statistics, 1956
- Approximation Methods which Converge with Probability oneThe Annals of Mathematical Statistics, 1954
- Stochastic Estimation of the Maximum of a Regression FunctionThe Annals of Mathematical Statistics, 1952
- A Stochastic Approximation MethodThe Annals of Mathematical Statistics, 1951