Stochastic approximation algorithms: Overview and recent trends

Bharath, B and Borkar, VS (1999) Stochastic approximation algorithms: Overview and recent trends. In: Sadhana, 24 (Part 4). pp. 425-452.

Preview

PDF saddhana1.pdf Download (2MB)

Abstract

Stochastic approximation is a common paradigm for many stochastic recursions arising both as algorithms and as models of some stochastic dynamic phenomena. This article gives an overview of the known results about their asymptotic behaviour, highlights recent developments such as distributed and multiscale algorithms, and describes existing and potential applications, and other related issues.

Item Type:	Journal Article
Publication:	Sadhana
Publisher:	Indian Academy of Sciences
Additional Information:	The copyright belongs to Indian Academy of Sciences.
Keywords:	Stochastic approximation;asymptotic convergence;stochastic optimization;learning algorithms
Department/Centre:	Division of Electrical Sciences > Electrical Communication Engineering Division of Electrical Sciences > Computer Science & Automation
Date Deposited:	07 Dec 2004
Last Modified:	19 Sep 2010 04:15
URI:	http://eprints.iisc.ac.in/id/eprint/1503

Actions (login required)

View Item