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, ENS Paris - École normale supérieure - Paris, 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.
Type de document :
Communication dans un congrès
33rd International Conference on Machine Learning (ICML 2016), Jun 2016, New York, NY, United States. 2016, Proceedings of the 33rd International Conference on Machine Learning
Liste complète des métadonnées

Littérature citée [47 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-01307045
Contributeur : Emilie Morvant <>
Soumis le : mardi 31 mai 2016 - 15:52:13
Dernière modification le : jeudi 11 janvier 2018 - 06:28:04
Document(s) archivé(s) le : jeudi 1 septembre 2016 - 11:36:03

Fichier

dalc_icml2016.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01307045, version 1

Collections

Citation

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. 2016, Proceedings of the 33rd International Conference on Machine Learning. 〈hal-01307045〉

Partager

Métriques

Consultations de la notice

204

Téléchargements de fichiers

121