PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

PAC-Bayes Analysis of Maximum Entropy Learning
John Shawe-Taylor and David Hardoon
In: 12th International Conference on Artificial Intelligence and Statistics(2008).


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.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Conference or Workshop Item (Poster)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Theory & Algorithms
ID Code:4665
Deposited By:David Hardoon
Deposited On:13 March 2009