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

Pascal Germain (1) , Amaury Habrard (2) , François Laviolette (1) , Emilie Morvant (2)

1 Department of Computer Science and Software Engineering [Québec]
2 LHC - Laboratoire Hubert Curien

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.

Domaines: Machine Learning [stat.ML]

Pascal Germain, Amaury Habrard, François Laviolette, Emilie Morvant. An Improvement to the Domain Adaptation Bound in a PAC-Bayesian context. NIPS 2014 Workshop on Transfer and Multi-task learning: Theory Meets Practice, Dec 2014, Montréal, Canada. ⟨hal-01093565v2⟩