National audienceNormalization flows are generic and powerful tools for probabilistic modeling and density estimation. In this paper, we show that this class of models can also be used to approximate the solution of an optimal transport problem between any empirical distributions. Specifically, the optimal transport plan is approximated by an invertible network whose training is based on the relaxation of the Monge formulation. This approach has the advantage of allowing a discretization of this transport plan into a composition of functions associated with each layer of the network, providing intermediate transports between two measures.Les flux de normalisation sont des outils génériques et puissants pour l'élaboration de modèles probabil...
Normalizing flows are constructed from a base distribution with a known density and a diffeomorphism...
This paper introduces the first statistically consistent estimator of the optimal transport map betw...
Monge map refers to the optimal transport map between two probability distributions and provides a p...
National audienceNormalization flows are generic and powerful tools for probabilistic modeling and d...
International audienceOptimal transport (OT) provides effective tools for comparing and mapping prob...
Optimal transport (OT) provides effective tools for comparing and mapping probability measures. We p...
15 pages, 4 figures. To appear in the Proceedings of the International Conference on Learning Repres...
The objective in statistical Optimal Transport (OT) is to consistently estimate the optimal transpor...
Optimal transport maps define a one-to-one correspondence between probability distributions, and as ...
Normalizing Flows (NF) are powerful likelihood-based generative models that are able to trade off be...
International audienceWe begin by improving some estimators of a model {Peje^Rd, then we give two me...
This thesis proposes theoretical and numerical contributions to use Entropy-regularized Optimal Tran...
Optimal Transport (OT) has recently gained increasing attention in various fields ranging from biolo...
This thesis proposes theoretical and numerical contributions to use Entropy-regularized Optimal Tran...
Normalizing flows are constructed from a base distribution with a known density and a diffeomorphism...
This paper introduces the first statistically consistent estimator of the optimal transport map betw...
Monge map refers to the optimal transport map between two probability distributions and provides a p...
National audienceNormalization flows are generic and powerful tools for probabilistic modeling and d...
International audienceOptimal transport (OT) provides effective tools for comparing and mapping prob...
Optimal transport (OT) provides effective tools for comparing and mapping probability measures. We p...
15 pages, 4 figures. To appear in the Proceedings of the International Conference on Learning Repres...
The objective in statistical Optimal Transport (OT) is to consistently estimate the optimal transpor...
Optimal transport maps define a one-to-one correspondence between probability distributions, and as ...
Normalizing Flows (NF) are powerful likelihood-based generative models that are able to trade off be...
International audienceWe begin by improving some estimators of a model {Peje^Rd, then we give two me...
This thesis proposes theoretical and numerical contributions to use Entropy-regularized Optimal Tran...
Optimal Transport (OT) has recently gained increasing attention in various fields ranging from biolo...
This thesis proposes theoretical and numerical contributions to use Entropy-regularized Optimal Tran...
Normalizing flows are constructed from a base distribution with a known density and a diffeomorphism...
This paper introduces the first statistically consistent estimator of the optimal transport map betw...
Monge map refers to the optimal transport map between two probability distributions and provides a p...