A Strong Approximation Theorem for Stochastic Recursive Algorithm

Borkar, VS and Mitter, SK (1999) A Strong Approximation Theorem for Stochastic Recursive Algorithm. In: Journal of Optimization Theory And Applications, 100 (3). pp. 499-513.

PDF fulltext.pdf - Published Version Restricted to Registered users only Download (543Kb) | Request a copy

Abstract

The constant stepsize analog of Gelfand-Mitter type discrete-time stochastic recursive algorithms is shown to track an associated stochastic differential equation in the strong sense, i.e., with respect to an appropriate divergence measure.

Item Type:	Journal Article
Additional Information:	Copyright of this article belongs to Springer.
Keywords:	Stochastic algorithms;Approximation of stochastic differential equations;Constant stepsize algorithms;Asymptotic behavior.
Department/Centre:	Division of Electrical Sciences > Computer Science & Automation (Formerly, School of Automation)
Date Deposited:	07 Jan 2010 09:09
Last Modified:	19 Sep 2010 04:59
URI:	http://eprints.iisc.ernet.in/id/eprint/18011

Actions (login required)

View Item