An Improvement to the Domain Adaptation Bound in a PAC-Bayesian context
Machine Learning
2015-01-14 v1 Machine Learning
Abstract
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.
Cite
@article{arxiv.1501.03002,
title = {An Improvement to the Domain Adaptation Bound in a PAC-Bayesian context},
author = {Pascal Germain and Amaury Habrard and Francois Laviolette and Emilie Morvant},
journal= {arXiv preprint arXiv:1501.03002},
year = {2015}
}
Comments
NIPS 2014 Workshop on Transfer and Multi-task learning: Theory Meets Practice, Dec 2014, Montr{\'e}al, Canada