Existence and consistency of Wasserstein barycenters

DOI10.1007/s00440-016-0727-zzbMath1406.60019arXiv1506.04153MaRDI QIDQ2363656

Thibaut Le Gouic, Jean-Michel Loubes

Publication date: 25 July 2017

Published in: Probability Theory and Related Fields (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1506.04153

zbMATH Keywords

existence; consistency; barycenter; Wasserstein distance; Fréchet mean

Mathematics Subject Classification ID

62H10: Multivariate distribution of statistics

62G20: Asymptotic properties of nonparametric inference

60D05: Geometric probability and stochastic geometry

Related Items

Characterization of barycenters in the Wasserstein space by averaging optimal transport maps, Fr\'echet barycenters in the Monge-Kantorovich spaces, Stochastic approximation versus sample average approximation for Wasserstein barycenters, Randomized Wasserstein Barycenter Computation: Resampling with Statistical Guarantees, Entropic-Wasserstein Barycenters: PDE Characterization, Regularity, and CLT, Nonpositive curvature, the variance functional, and the Wasserstein barycenter, Penalization of Barycenters in the Wasserstein Space, Wasserstein barycenters in the manifold of all positive definite matrices, Geometric Averages of Partitioned Datasets, Regularizing Orientation Estimation in Cryogenic Electron Microscopy Three-Dimensional Map Refinement through Measure-Based Lifting over Riemannian Manifolds, $W_2$ barycenters for radially related distributions, Machine learning and optimal transport: some statistical and algorithmic tools, Fast convergence of empirical barycenters in Alexandrov spaces and the Wasserstein space, Distances and isomorphism between networks: stability and convergence of network invariants, Bayesian learning with Wasserstein barycenters, Quantitative stability of barycenters in the Wasserstein space, A fixed-point approach to barycenters in Wasserstein space, Fréchet means and Procrustes analysis in Wasserstein space, Central limit theorem and bootstrap procedure for Wasserstein's variations with an application to structural relationships between distributions, The coupling method in extreme value theory, Clustering patterns connecting COVID-19 dynamics and human mobility using optimal transport, A minimax framework for quantifying risk-fairness trade-off in regression, Kantorovich-Rubinstein distance and barycenter for finitely supported measures: foundations and algorithms, Minimax estimation of smooth densities in Wasserstein distance, Uniform convergence of local Fréchet regression with applications to locating extrema and time warping for metric space valued trajectories, Convergence rates for empirical barycenters in metric spaces: curvature, convexity and extendable geodesics, Gaussian processes with multidimensional distribution inputs via optimal transport and Hilbertian embedding, Barycenters in the Hellinger-Kantorovich space, Statistical inference for Bures-Wasserstein barycenters, On the computation of Wasserstein barycenters, Procrustes metrics on covariance operators and optimal transportation of Gaussian processes, On the analysis of adaptability in multi-source domain adaptation, Robust clustering tools based on optimal transportation, Parseval's identity and optimal transport maps, Elements of Statistical Inference in 2-Wasserstein Space, Barycenters for the Hellinger--Kantorovich Distance Over $\mathbb{R}^d$, On clustering uncertain and structured data with Wasserstein barycenters and a geodesic criterion for the number of clusters

Uses Software

fda (R)

Cites Work