ML Anthology

PAC-Bayesian Learning of Linear Classifiers

Pascal Germain, Alexandre Lacasse, François Laviolette, Mario Marchand
ICML 2009 pp. 353-360
doi:10.1145/1553374.1553419 /icml/2009/germain2009icml-pac/

Abstract

We present a general PAC-Bayes theorem from which all known PAC-Bayes bounds are simply obtained as particular cases. We also propose different learning algorithms for finding linear classifiers that minimize these PAC-Bayes risk bounds. These learning algorithms are generally competitive with both AdaBoost and the SVM.

PDF ICML Semantic Scholar

Cite

Text

Germain et al. "PAC-Bayesian Learning of Linear Classifiers." International Conference on Machine Learning, 2009. doi:10.1145/1553374.1553419

Markdown

[Germain et al. "PAC-Bayesian Learning of Linear Classifiers." International Conference on Machine Learning, 2009.](https://mlanthology.org/icml/2009/germain2009icml-pac/) doi:10.1145/1553374.1553419

BibTeX

@inproceedings{germain2009icml-pac,
  title     = {{PAC-Bayesian Learning of Linear Classifiers}},
  author    = {Germain, Pascal and Lacasse, Alexandre and Laviolette, François and Marchand, Mario},
  booktitle = {International Conference on Machine Learning},
  year      = {2009},
  pages     = {353-360},
  doi       = {10.1145/1553374.1553419},
  url       = {https://mlanthology.org/icml/2009/germain2009icml-pac/}
}