An Improvement to the Domain Adaptation Bound in a PAC-Bayesian context

Germain, Pascal, Habrard, Amaury, Laviolette, Francois, Morvant, Emilie Machine Learning 

This paper provides a theoretical analysis of domain adaptation based on the PAC-Bayesian theory. We propose an improvement of the previous domain adaptation bound obtained by Germain et al. in two ways. We first give another generalization bound tighter and easier to interpret. Moreover, we provide a new analysis of the constant term appearing in the bound that can be of high interest for developing new algorithmic solutions.