{PAC-Bayesian Theory for Transductive Learning}
Luc Bégin, Pascal Germain, François Laviolette, Jean-Francis Roy · International Conference on Artificial Intelligence and Statistics · 2014
We propose a PAC-Bayesian analysis of the transductive learning setting, introduced by Vapnik [1998], 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.