ML Anthology

A PAC-Bayes Approach to the Set Covering Machine

François Laviolette, Mario Marchand, Mohak Shah
NeurIPS 2005 pp. 731-738
/neurips/2005/laviolette2005neurips-pacbayes/

Abstract

We design a new learning algorithm for the Set Covering Ma- chine from a PAC-Bayes perspective and propose a PAC-Bayes risk bound which is minimized for classifiers achieving a non trivial margin-sparsity trade-off.

PDF NeurIPS Semantic Scholar

Cite

Text

Laviolette et al. "A PAC-Bayes Approach to the Set Covering Machine." Neural Information Processing Systems, 2005.

Markdown

[Laviolette et al. "A PAC-Bayes Approach to the Set Covering Machine." Neural Information Processing Systems, 2005.](https://mlanthology.org/neurips/2005/laviolette2005neurips-pacbayes/)

BibTeX

@inproceedings{laviolette2005neurips-pacbayes,
  title     = {{A PAC-Bayes Approach to the Set Covering Machine}},
  author    = {Laviolette, François and Marchand, Mario and Shah, Mohak},
  booktitle = {Neural Information Processing Systems},
  year      = {2005},
  pages     = {731-738},
  url       = {https://mlanthology.org/neurips/2005/laviolette2005neurips-pacbayes/}
}