Add to ORKGWe consider the problem of finding the barycenter of a finite set of probabilities on Rd with respect to the Wasserstein metric. We introduce an iterative procedure which consistenly ap-proximates the barycenter under general conditions. These cover the case of probabilities in a location-scatter family, including the Gaussian case. The performance of the iterative procedure is illustrated through numerical simulations, which show fast convergence towards the barycenter
International audienceIn this paper, based on the Fréchet mean, we define a notion of barycenter cor...
The Wasserstein distance is an attractive tool for data analysis but statistical inference is hinder...
In this work we introduce the concept of Bures--Wasserstein barycenter $Q_*$, that is essentially a ...
This paper presents primal heuristics for the computation of Wasserstein Barycenters of a given set ...
We define a notion of barycenter for random probability measures in the Wasserstein space. We give a...
The concept of barycenter in the Wasserstein space corresponds to define a notion of Fréchet mean of...
Cette thèse se concentre sur l'analyse de données présentées sous forme de mesures de probabilité su...
This paper is focused on the statistical analysis of probability measures $\bnu_{1},\ldots,\bnu_{n}$...
We present new algorithms to compute the mean of a set of empirical probability measures under the o...
We present new algorithms to compute the mean of a set of N empirical probability measures under the...
International audienceThis paper is concerned by the study of barycenters for random probability mea...
This paper presents a family of generative Linear Programming models that permit to compute the exac...
We present and study a novel algorithm for the computation of 2-Wasserstein population barycenters. ...
This paper is concerned by statistical inference problems from a data set whose elements may be mode...
We consider in this talk the inverse problem behind Wasserstein barycenters. Given a family of measu...
International audienceIn this paper, based on the Fréchet mean, we define a notion of barycenter cor...
The Wasserstein distance is an attractive tool for data analysis but statistical inference is hinder...
In this work we introduce the concept of Bures--Wasserstein barycenter $Q_*$, that is essentially a ...
This paper presents primal heuristics for the computation of Wasserstein Barycenters of a given set ...
We define a notion of barycenter for random probability measures in the Wasserstein space. We give a...
The concept of barycenter in the Wasserstein space corresponds to define a notion of Fréchet mean of...
Cette thèse se concentre sur l'analyse de données présentées sous forme de mesures de probabilité su...
This paper is focused on the statistical analysis of probability measures $\bnu_{1},\ldots,\bnu_{n}$...
We present new algorithms to compute the mean of a set of empirical probability measures under the o...
We present new algorithms to compute the mean of a set of N empirical probability measures under the...
International audienceThis paper is concerned by the study of barycenters for random probability mea...
This paper presents a family of generative Linear Programming models that permit to compute the exac...
We present and study a novel algorithm for the computation of 2-Wasserstein population barycenters. ...
This paper is concerned by statistical inference problems from a data set whose elements may be mode...
We consider in this talk the inverse problem behind Wasserstein barycenters. Given a family of measu...
International audienceIn this paper, based on the Fréchet mean, we define a notion of barycenter cor...
The Wasserstein distance is an attractive tool for data analysis but statistical inference is hinder...
In this work we introduce the concept of Bures--Wasserstein barycenter $Q_*$, that is essentially a ...