Characterization of barycenters in the Wasserstein space by averaging optimal transport maps
From MaRDI portal
Publication:4615429
Abstract: This paper is concerned by the study of barycenters for random probability measures in the Wasserstein space. Using a duality argument, we give a precise characterization of the population barycenter for various parametric classes of random probability measures with compact support. In particular, we make a connection between averaging in the Wasserstein space as introduced in Agueh and Carlier (2011), and taking the expectation of optimal transport maps with respect to a fixed reference measure. We also discuss the usefulness of this approach in statistics for the analysis of deformable models in signal and image processing. In this setting, the problem of estimating a population barycenter from n independent and identically distributed random probability measures is also considered.
Recommendations
Cites work
- scientific article; zbMATH DE number 469369 (Why is no real title available?)
- scientific article; zbMATH DE number 523032 (Why is no real title available?)
- scientific article; zbMATH DE number 2051142 (Why is no real title available?)
- scientific article; zbMATH DE number 1376935 (Why is no real title available?)
- scientific article; zbMATH DE number 1909499 (Why is no real title available?)
- scientific article; zbMATH DE number 2100538 (Why is no real title available?)
- scientific article; zbMATH DE number 3268526 (Why is no real title available?)
- scientific article; zbMATH DE number 3053873 (Why is no real title available?)
- A deconvolution approach to estimation of a common shape in a shifted curves model
- A fixed-point approach to barycenters in Wasserstein space
- A parametric registration model for warped distributions with Wasserstein's distance
- Barycenters in the Wasserstein space
- Distribution's template estimate with Wasserstein metrics
- Efficient estimation for a subclass of shape invariant models
- Existence and consistency of Wasserstein barycenters
- Intrinsic inference on the mean geodesic of planar shapes and tree discrimination by leaf growth
- Iterative Bregman projections for regularized transportation problems
- Large sample theory of intrinsic and extrinsic sample means on manifolds. I
- Large sample theory of intrinsic and extrinsic sample means on manifolds. II.
- Local Geometry of Deformable Templates
- Measurability of optimal transportation and strong coupling of martingale measures
- On a product of positive semidefinite matrices
- On the consistency of Fréchet means in deformable models for curve and image analysis
- One-dimensional empirical measures, order statistics, and Kantorovich transport distances
- Optimal mass transport for registration and warping
- Optimal transportation with infinitely many marginals
- Pattern theory. From representation to inference.
- Polar factorization and monotone rearrangement of vector‐valued functions
- Relations between Weak and Uniform Convergence of Measures with Applications
- Riemannian \(L^{p}\) center of mass: existence, uniqueness, and convexity
- Semi-parametric estimation of shifts
- Semiparametric estimation of shifts on compact Lie groups for image registration
- Shape Manifolds, Procrustean Metrics, and Complex Projective Spaces
- Shape Spaces
- Sliced and Radon Wasserstein barycenters of measures
- Statistical M-estimation and consistency in large deformable models for image warping
- Statistical models for deformable templates in image and shape analysis
- Stochastic algorithms for computing means of probability measures
- Strong law of large numbers for measures of central tendency and dispersion of random variables in compact metric spaces
- The Monge-Ampère equation and its link to optimal transportation
- Towards a Coherent Statistical Framework for Dense Deformable Template Estimation
- Uniqueness and approximate computation of optimal incomplete transportation plans
- Wasserstein barycenters over Riemannian manifolds
Cited in
(25)- Distributionally robust portfolio maximization and marginal utility pricing in one period financial markets
- Global sensitivity analysis and Wasserstein spaces
- Elements of statistical inference in 2-Wasserstein space
- Entropic approximation of Wasserstein gradient flows
- Simple approximative algorithms for free-support Wasserstein barycenters
- Randomized Wasserstein barycenter computation: resampling with statistical guarantees
- scientific article; zbMATH DE number 7370538 (Why is no real title available?)
- Optimal transport and barycenters for dendritic measures
- Hellinger–Kantorovich barycenter between Dirac measures
- Penalization of barycenters in the Wasserstein space
- Quantitative stability of barycenters in the Wasserstein space
- Entropic-Wasserstein barycenters: PDE characterization, regularity, and CLT
- Gaussian processes with multidimensional distribution inputs via optimal transport and Hilbertian embedding
- Barycenters for the Hellinger-Kantorovich distance over \(\mathbb{R}^d\)
- Distribution's template estimate with Wasserstein metrics
- Procrustes metrics on covariance operators and optimal transportation of Gaussian processes
- Linearized optimal transport on manifolds
- Existence and consistency of Wasserstein barycenters
- \(W_2\) barycenters for radially related distributions
- Bayesian learning with Wasserstein barycenters
- Towards a central limit theorem in the Wasserstein space?
- Fréchet barycenters in the Monge-Kantorovich spaces
- Unbalanced optimal total variation transport problems and generalized Wasserstein barycenters
- Central limit theorem and bootstrap procedure for Wasserstein's variations with an application to structural relationships between distributions
- Stochastic approximation versus sample average approximation for Wasserstein barycenters
This page was built for publication: Characterization of barycenters in the Wasserstein space by averaging optimal transport maps
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4615429)
