Timezone: »

Unbalanced minibatch Optimal Transport; applications to Domain Adaptation
Kilian Fatras · Thibault Séjourné · Rémi Flamary · Nicolas Courty

Tue Jul 20 05:40 AM -- 05:45 AM (PDT) @ None

Optimal transport distances have found many applications in machine learning for their capacity to compare non-parametric probability distributions. Yet their algorithmic complexity generally prevents their direct use on large scale datasets. Among the possible strategies to alleviate this issue, practitioners can rely on computing estimates of these distances over subsets of data, i.e. minibatches. While computationally appealing, we highlight in this paper some limits of this strategy, arguing it can lead to undesirable smoothing effects. As an alternative, we suggest that the same minibatch strategy coupled with unbalanced optimal transport can yield more robust behaviors. We discuss the associated theoretical properties, such as unbiased estimators, existence of gradients and concentration bounds. Our experimental study shows that in challenging problems associated to domain adaptation, the use of unbalanced optimal transport leads to significantly better results, competing with or surpassing recent baselines.

Author Information

Kilian Fatras (IRISA/INRIA)
Thibault Séjourné (CNRS, Projet NORIA, ENS, PSL)
Rémi Flamary (École Polytechnique)
Nicolas Courty (UBS)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors