PAC-Bayesian Theory for Transductive Learning
Abstract
We propose a PAC-Bayesian analysis of the transductive learning setting, introduced by Vapnik [2008], by proposing a family of new bounds on the generalization error. Some of them are derived from their counterpart in the inductive setting, and others are new. We also compare their behavior.
Cite
Text
Bégin et al. "PAC-Bayesian Theory for Transductive Learning." International Conference on Artificial Intelligence and Statistics, 2014.Markdown
[Bégin et al. "PAC-Bayesian Theory for Transductive Learning." International Conference on Artificial Intelligence and Statistics, 2014.](https://mlanthology.org/aistats/2014/begin2014aistats-pac/)BibTeX
@inproceedings{begin2014aistats-pac,
title = {{PAC-Bayesian Theory for Transductive Learning}},
author = {Bégin, Luc and Germain, Pascal and Laviolette, François and Roy, Jean-Francis},
booktitle = {International Conference on Artificial Intelligence and Statistics},
year = {2014},
pages = {105-113},
url = {https://mlanthology.org/aistats/2014/begin2014aistats-pac/}
}