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.
|EPrint Type:||Conference or Workshop Item (Poster)|
|Project Keyword:||Project Keyword UNSPECIFIED|
|Subjects:||Theory & Algorithms|
|Deposited By:||David Hardoon|
|Deposited On:||13 March 2009|