2 search results - page 1 / 1 » PAC-Bayes risk bounds for sample-compressed Gibbs classifier... |
ICML
2007
IEEE
16 years 17 days ago
2007
IEEE
We propose a formulation of the Decision Tree learning algorithm in the Compression settings and derive tight generalization error bounds. In particular, we propose Sample Compres...
67
Voted
ICML
2005
IEEE
16 years 17 days ago
2005
IEEE
We extend the PAC-Bayes theorem to the sample-compression setting where each classifier is represented by two independent sources of information: a compression set which consists ...