PAC-Bayes analysis of maximum entropy learning.
Journal of Machine Learning Research.
(pp. 480 - 487).
We extend and apply the PAC-Bayes theorem to the analysis of maximum entropy learning by considering maximum entropy classification. The theory introduces a multiple sampling technique that controls an effective margin of the bound. We further develop a dual implementation of the convex optimisation that optimises the bound. This algorithm is tested on some simple datasets and the value of the bound compared with the test error.© 2009 by the authors.
|Title:||PAC-Bayes analysis of maximum entropy learning|
|Open access status:||An open access publication|
|UCL classification:||UCL > School of BEAMS > Faculty of Engineering Science > Computer Science|
Archive Staff Only