Search Machine Learning Repository: A PAC-Bayesian Approach for Domain Adaptation with Specialization to Linear Classifiers
Authors: Pascal Germain, Amaury Habrard, Franois Laviolette and Emilie Morvant
Conference: Proceedings of the 30th International Conference on Machine Learning (ICML-13)
Year: 2013
Pages: 738-746
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.
[pdf] [BibTeX]

authors venues years
Suggest Changes to this paper.
Brought to you by the WUSTL Machine Learning Group. We have open faculty positions (tenured and tenure-track).