A New PAC-Bayesian Perspective on Domain Adaptation

Pascal Germain 1 Amaury Habrard 2 François Laviolette 3 Emilie Morvant 2
1 SIERRA - Statistical Machine Learning and Parsimony
DI-ENS - Département d'informatique de l'École normale supérieure, CNRS - Centre National de la Recherche Scientifique, Inria de Paris
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 algorithm and perform experiments on real data.
Complete list of metadatas

Cited literature [47 references]  Display  Hide  Download

Contributor : Emilie Morvant <>
Submitted on : Tuesday, May 31, 2016 - 3:52:13 PM
Last modification on : Thursday, February 7, 2019 - 2:42:36 PM
Long-term archiving on : Thursday, September 1, 2016 - 11:36:03 AM


Files produced by the author(s)


  • HAL Id : hal-01307045, version 1


Pascal Germain, Amaury Habrard, François Laviolette, Emilie Morvant. A New PAC-Bayesian Perspective on Domain Adaptation. 33rd International Conference on Machine Learning (ICML 2016), Jun 2016, New York, NY, United States. ⟨hal-01307045⟩



Record views


Files downloads