English

A New PAC-Bayesian Perspective on Domain Adaptation

Machine Learning 2016-07-27 v4 Machine Learning

Abstract

We study the issue of PAC-Bayesian domain adaptation: We want to learn, from a source domain, a majority vote model dedicated to a target one. Our theoretical contribution brings a new perspective by deriving an upper-bound on the target risk where the distributions' divergence---expressed as a ratio---controls the trade-off between a source error measure and the target voters' disagreement. Our bound suggests that one has to focus on regions where the source data is informative.From this result, we derive a PAC-Bayesian generalization bound, and specialize it to linear classifiers. Then, we infer a learning algorithmand perform experiments on real data.

Keywords

Cite

@article{arxiv.1506.04573,
  title  = {A New PAC-Bayesian Perspective on Domain Adaptation},
  author = {Pascal Germain and Amaury Habrard and François Laviolette and Emilie Morvant},
  journal= {arXiv preprint arXiv:1506.04573},
  year   = {2016}
}

Comments

Published at ICML 2016

R2 v1 2026-06-22T09:53:42.493Z