Timezone: »

 
Poster
Joint distribution optimal transportation for domain adaptation
Nicolas Courty · Rémi Flamary · Amaury Habrard · Alain Rakotomamonjy

Mon Dec 04 06:30 PM -- 10:30 PM (PST) @ Pacific Ballroom #6
in Posters Mon »
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 $\ps$ and $\pt$. We propose a solution of this problem with optimal transport, that allows to recover an estimated target $\pt^f=(X,f(X))$ 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.
Keywords: Learning Theory · Multitask and Transfer Learning
[ Code]  [ Paper] 

Author Information

Nicolas Courty (IRISA / University South Brittany)
Rémi Flamary (Université Côte d'Azur)
Amaury Habrard (University of Saint-Etienne, Univ. Lyon, Lab. H Curien, France)
Alain Rakotomamonjy (Université de Rouen Normandie)

More from the Same Authors