PAC-Bayes and 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 provide two main contributions in PAC-Bayesian theory for domain adaptation where the objective is to learn, from a source distribution, a well-performing majority vote on a different, but related, target distribution. Firstly, we propose an improvement of the previous approach we proposed in Germain et al. (2013), which relies on a novel distribution pseudodistance based on a disagreement averaging, allowing us to derive a new tighter domain adaptation bound for the target risk. While this bound stands in the spirit of common domain adaptation works, we derive a second bound (recently introduced in Germain et al., 2016) that brings a new perspective on domain adaptation 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. We discuss and compare both results, from which we obtain PAC-Bayesian generalization bounds. Furthermore, from the PAC-Bayesian specialization to linear classifiers, we infer two learning algorithms, and we evaluate them on real data.
Type de document :
Pré-publication, Document de travail
Liste complète des métadonnées
Contributeur : Emilie Morvant <>
Soumis le : lundi 17 juillet 2017 - 12:30:39
Dernière modification le : jeudi 26 juillet 2018 - 01:10:47
Document(s) archivé(s) le : samedi 27 janvier 2018 - 03:21:21


Fichiers produits par l'(les) auteur(s)


  • HAL Id : hal-01563152, version 1
  • ARXIV : 1707.05712


Pascal Germain, Amaury Habrard, François Laviolette, Emilie Morvant. PAC-Bayes and Domain Adaptation. 2017. 〈hal-01563152〉



Consultations de la notice


Téléchargements de fichiers