A PAC-Bayesian Approach for Domain Adaptation with Specialization to Linear Classifiers

Abstract

We provide a first PAC-Bayesian analysis for domain adaptation (DA) which arises when the learning and test distributions differ. It relies on a novel distribution pseudodistance based on a disagreement averaging. Using this measure, we derive a PAC-Bayesian DA bound for the stochastic Gibbs classifier. This bound has the advantage of being directly optimizable for any hypothesis space. We specialize it to linear classifiers, and design a learning algorithm which shows interesting results on a synthetic problem and on a popular sentiment annotation task. This opens the door to tackling DA tasks by making use of all the PAC-Bayesian tools.

Cite

Text

Germain et al. "A PAC-Bayesian Approach for Domain Adaptation with Specialization to Linear Classifiers." International Conference on Machine Learning, 2013.

Markdown

[Germain et al. "A PAC-Bayesian Approach for Domain Adaptation with Specialization to Linear Classifiers." International Conference on Machine Learning, 2013.](https://mlanthology.org/icml/2013/germain2013icml-pacbayesian/)

BibTeX

@inproceedings{germain2013icml-pacbayesian,
  title     = {{A PAC-Bayesian Approach for Domain Adaptation with Specialization to Linear Classifiers}},
  author    = {Germain, Pascal and Habrard, Amaury and Laviolette, François and Morvant, Emilie},
  booktitle = {International Conference on Machine Learning},
  year      = {2013},
  pages     = {738-746},
  volume    = {28},
  url       = {https://mlanthology.org/icml/2013/germain2013icml-pacbayesian/}
}