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.
[ Link to text file ]
<< Go back.