Joint distribution optimal transportation for domain adaptation - Normandie Université Accéder directement au contenu
Communication Dans Un Congrès Année : 2017

Joint distribution optimal transportation for domain adaptation

Résumé

This paper deals with the unsupervised domain adaptation problem, where one wants to estimate a prediction function f in a given target domain without any labeled sample by exploiting the knowledge available from a source domain where labels are known. Our work makes the following assumption: there exists a non-linear transformation between the joint feature/label space distributions of the two domain P s and P t that can be estimated with optimal transport. We propose a solution of this problem that allows to recover an estimated target P f t = (X, f (X)) by optimizing simultaneously the optimal coupling and f. We show that our method corresponds to the minimization of a bound on the target error, and provide an efficient algorithmic solution, for which convergence is proved. The versatility of our approach, both in terms of class of hypothesis or loss functions is demonstrated with real world classification and regression problems, for which we reach or surpass state-of-the-art results.
Fichier principal
Vignette du fichier
jdot.pdf (637.43 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01620589 , version 1 (20-10-2017)

Identifiants

  • HAL Id : hal-01620589 , version 1

Citer

Nicolas Courty, Rémi Flamary, Amaury Habrard, Alain Rakotomamonjy. Joint distribution optimal transportation for domain adaptation. NIPS 2017, Dec 2017, Los Angeles, United States. ⟨hal-01620589⟩
351 Consultations
420 Téléchargements

Partager

Gmail Facebook X LinkedIn More