Prior knowledge and preferential structures in gradient descent learning algorithms
Download (475.21 kB)
-
Altmetric Citations
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]
Collections | ANU 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 | Size | Format | Image |
---|---|---|---|---|
Mahony_Prior2001.pdf | 475.21 kB | Adobe PDF | ![]() |
Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.
Updated: 19 May 2020/ Responsible Officer: University Librarian/ Page Contact: Library Systems & Web Coordinator