PAC-Bayesian learning of linear classifiers
PAC-Bayesian learning of linear classifiers
Pascal Germain,A. Lacasse,François Laviolette,M. Marchand
2009 · DOI: 10.1145/1553374.1553419
International Conference on Machine Learning · 267 Citations
TLDR
A general PAC- Bayes theorem is presented from which all known PAC-Bayes risk bounds are obtained as particular cases and different learning algorithms for finding linear classifiers that minimize these bounds are proposed.