Skip navigation
Skip navigation

Prior knowledge and preferential structures in gradient descent learning algorithms

Mahony, Robert; Williamson, Robert

Description

A family of gradient descent algorithms for learning linear functions in an online setting is considered. The family includes the classical LMS algorithm as well as new variants such as the Exponentiated Gradient (EG) algorithm due to Kivinen and Warmuth. The algorithms are based on prior distributions defined on the weight space. Techniques from differential geometry are used to develop the algorithms as gradient descent iterations with respect to the natural gradient in the Riemannian...[Show more]

CollectionsANU Research Publications
Date published: 2001-09
Type: Journal article
URI: http://hdl.handle.net/10440/305
http://digitalcollections.anu.edu.au/handle/10440/305
Source: Journal of Machine Learning Research
DOI: 10.1162/153244301753683735

Download

File Description SizeFormat Image
Mahony_Prior2001.pdf475.21 kBAdobe PDFThumbnail


Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.

Updated:  20 July 2017/ Responsible Officer:  University Librarian/ Page Contact:  Library Systems & Web Coordinator