Two timescale analysis of the Alopex algorithm for optimization

Sastry, PS and Magesh, M and Unnikrishnan, KP (2002) Two timescale analysis of the Alopex algorithm for optimization. In: Neural Computation, 14 (11). pp. 2729-2750.

PDF Two_Timescale_Analysis.pdf - Published Version Restricted to Registered users only Download (174kB) | Request a copy

Abstract

Alopex is a correlation-based gradient-free optimization technique useful in many learning problems. However, there are no analytical results on the asymptotic behavior of this algorithm. This article presents a new version of Alopex that can be analyzed using techniques of two timescale stochastic approximation method. It is shown that the algorithm asymptotically behaves like a gradient-descent method, though it does not need (or estimate) any gradient information. It is also shown, through simulations, that the algorithm is quite effective.

Item Type:	Journal Article
Publication:	Neural Computation
Publisher:	MIT Press
Additional Information:	Copyright of this article belongs to MIT Press.
Department/Centre:	Division of Electrical Sciences > Electrical Engineering
Date Deposited:	28 Jul 2011 04:32
Last Modified:	28 Jul 2011 04:32
URI:	http://eprints.iisc.ac.in/id/eprint/39509

Actions (login required)

View Item