The Annals of Mathematical Statistics

A Stochastic Approximation Method

Abstract

Let $M(x)$ denote the expected value at level $x$ of the response to a certain experiment. $M(x)$ is assumed to be a monotone function of $x$ but is unknown to the experimenter, and it is desired to find the solution $x = \theta$ of the equation $M(x) = \alpha$, where $\alpha$ is a given constant. We give a method for making successive experiments at levels $x_1,x_2,\cdots$ in such a way that $x_n$ will tend to $\theta$ in probability.

Article information

Source
Ann. Math. Statist. Volume 22, Number 3 (1951), 400-407.

Dates
First available in Project Euclid: 28 April 2007

http://projecteuclid.org/euclid.aoms/1177729586

Digital Object Identifier
doi:10.1214/aoms/1177729586

Mathematical Reviews number (MathSciNet)
MR42668

Zentralblatt MATH identifier
0054.05901

JSTOR

Citation

Robbins, Herbert; Monro, Sutton. A Stochastic Approximation Method. Ann. Math. Statist. 22 (1951), no. 3, 400--407. doi:10.1214/aoms/1177729586. http://projecteuclid.org/euclid.aoms/1177729586.