PAC-Bayesian Theory for Transductive Learning
; Proceedings of the Seventeenth International Conference on Artificial Intelligence and Statistics, PMLR 33:105-113, 2014.
We propose a PAC-Bayesian analysis of the transductive learning setting, introduced by Vapnik , 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.