Existence and consistency of Wasserstein barycenters

@article{LeGouic2015ExistenceAC,
  title={Existence and consistency of Wasserstein barycenters},
  author={Thibaut Le Gouic and Jean-Michel Loubes},
  journal={Probability Theory and Related Fields},
  year={2015},
  volume={168},
  pages={901-917}
}
Based on the Fréchet mean, we define a notion of barycenter corresponding to a usual notion of statistical mean. We prove the existence of Wasserstein barycenters of random probabilities defined on a geodesic space (E, d). We also prove the consistency of this barycenter in a general setting, that includes taking barycenters of empirical versions of the probability measures or of a growing set of probability measures. 
Fast convergence of empirical barycenters in Alexandrov spaces and the Wasserstein space
This work establishes fast, i.e., parametric, rates of convergence for empirical barycenters over a large class of geodesic spaces with curvature bounds in the sense of Alexandrov. More specifically,
Barycenters in generalized Wasserstein spaces
TLDR
This article shows the existence of barycenters for measures with compact supports, and investigates a dual problem of the barycenter problem via the Kantorovich duality formula for generalized Wasserstein distances.
Entropic-Wasserstein Barycenters: PDE Characterization, Regularity, and CLT
TLDR
This paper characterizes Wasserstein barycenters in terms of a system of Monge–Ampère equations, and proves some global moment and Sobolev bounds as well as higher regularity properties.
Gradient descent algorithms for Bures-Wasserstein barycenters
TLDR
A framework to derive global rates of convergence for both gradient descent and stochastic gradient descent despite the fact that the barycenter functional is not geodesically convex is developed by employing a Polyak-Lojasiewicz (PL) inequality.
Penalization of Barycenters in the Wasserstein Space
TLDR
A regularization of Wasserstein barycenters for random measures supported on $\mathbb{R}^{d}$ is introduced via convex penalization.
Fr\'echet Barycenters and a Law of Large Numbers for Measures on the Real Line
Endow the space P(R) of probability measures on R with a transportation cost J(μ, ν) generated by a translation-invariant convex cost function. For a probability distribution on P(R) we formulate a
Barycenters in the Hellinger-Kantorovich space.
Barycenters in the Hellinger–Kantorovich Space
Recently, Liero, Mielke and Savaré introduced the Hellinger–Kantorovich distance on the space of nonnegative Radon measures of a metric space X . We prove that Hellinger–Kantorovich barycenters
On the Computation of Wasserstein Barycenters
TLDR
A general version of the equivalence of the Wasserstein barycenter problem to the n -coupling problem is state, which provides as a main contribution the simple to implement iterative swapping algorithm (ISA) for computing barycenters.
Sampling From the Wasserstein Barycenter
TLDR
It is proved that the minimum of this penalized multimarginal formulation is achieved for a coupling that is close to the Wasserstein barycenter, with an additive penalization to account for the marginal constraints.
...
...

References

SHOWING 1-10 OF 40 REFERENCES
Barycenters in the Wasserstein Space
TLDR
This paper provides existence, uniqueness, characterizations, and regularity of the barycenter and relates it to the multimarginal optimal transport problem considered by Gangbo and Świech in [Comm. Pure Appl. Math., 51 (1998), pp. 23–45].
Barycenters in Alexandrov spaces of curvature bounded below
We investigate barycenters of probability measures on proper Alexandrov spaces of curvature bounded below, and show that they enjoy several properties relevant to or different from those in metric
Consistent estimation of a population barycenter in the Wasserstein space
TLDR
Using a duality argument, a precise characterization of the population barycenter for compactly supported measures is given, and a connection between averaging in the Wasserstein space and taking the expectation of optimal transport maps is made.
Distribution's template estimate with Wasserstein metrics
TLDR
Using barycenters of measures in the Wasserstein space, an iterative version as an estimation of the mean distribution is proposed, when the distributions are a common measure warped by a centered random operator, then the barycenter enables to recover this distribution template.
A statistical analysis of a deformation model with Wasserstein barycenters : estimation procedure and goodness of fit test
TLDR
The asymptotic distribution and a bootstrap procedure for the Wasserstein variation are obtained and a criterion which studies the Frechet mean (or barycenter) of the warped distributions whose study enables to make inference on the model is considered.
Probability Measures on Metric Spaces of Nonpositive Curvature
We present an introduction to metric spaces of nonpositive curvature (”NPC spaces”) and a discussion of barycenters of probability measures on such spaces. In our introduction to NPC spaces, we will
Ricci curvature for metric-measure spaces via optimal transport
We dene a notion of a measured length space X having nonnegative N-Ricci curvature, for N 2 [1;1), or having1-Ricci curvature bounded below byK, forK2 R. The denitions are in terms of the
Gradient Flows: In Metric Spaces and in the Space of Probability Measures
Notation.- Notation.- Gradient Flow in Metric Spaces.- Curves and Gradients in Metric Spaces.- Existence of Curves of Maximal Slope and their Variational Approximation.- Proofs of the Convergence
...
...