Characterization of barycenters in the Wasserstein space by averaging optimal transport maps
From MaRDI portal
Publication:4615429
DOI10.1051/PS/2017020zbMATH Open1409.62049arXiv1212.2562OpenAlexW1536509825MaRDI QIDQ4615429FDOQ4615429
Publication date: 28 January 2019
Published in: ESAIM: Probability and Statistics (Search for Journal in Brave)
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.
Full work available at URL: https://arxiv.org/abs/1212.2562
Recommendations
optimal transportWasserstein spacedualitydeformable modelsconvergence of random variablesFréchet meancurve and image warpingempirical and population barycentersparametric classes of random probability measures
Nonparametric estimation (62G05) Directional data; spatial statistics (62H11) Asymptotic distribution theory in statistics (62E20) Variational problems in a geometric measure-theoretic setting (49Q20) Random measures (60G57)
Cites Work
- Pattern theory. From representation to inference.
- Shape Manifolds, Procrustean Metrics, and Complex Projective Spaces
- Relations between Weak and Uniform Convergence of Measures with Applications
- Barycenters in the Wasserstein Space
- Polar factorization and monotone rearrangement of vector‐valued functions
- Stochastic algorithms for computing means of probability measures
- Title not available (Why is that?)
- Title not available (Why is that?)
- Large sample theory of intrinsic and extrinsic sample means on manifolds. I
- Riemannian $L^{p}$ center of mass: Existence, uniqueness, and convexity
- Title not available (Why is that?)
- Title not available (Why is that?)
- Existence and consistency of Wasserstein barycenters
- A fixed-point approach to barycenters in Wasserstein space
- The Monge–Ampère equation and its link to optimal transportation
- Title not available (Why is that?)
- Iterative Bregman Projections for Regularized Transportation Problems
- Uniqueness and approximate computation of optimal incomplete transportation plans
- Distribution's template estimate with Wasserstein metrics
- Sliced and Radon Wasserstein barycenters of measures
- Large sample theory of intrinsic and extrinsic sample means on manifolds. II.
- Optimal mass transport for registration and warping
- Local Geometry of Deformable Templates
- On a product of positive semidefinite matrices
- A parametric registration model for warped distributions with Wasserstein's distance
- One-dimensional empirical measures, order statistics, and Kantorovich transport distances
- Optimal transportation with infinitely many marginals
- Title not available (Why is that?)
- On the consistency of Fréchet means in deformable models for curve and image analysis
- Semi-parametric estimation of shifts
- Semiparametric estimation of shifts on compact Lie groups for image registration
- Title not available (Why is that?)
- Shape Spaces
- Intrinsic inference on the mean geodesic of planar shapes and tree discrimination by leaf growth
- Efficient estimation for a subclass of shape invariant models
- A deconvolution approach to estimation of a common shape in a shifted curves model
- Strong law of large numbers for measures of central tendency and dispersion of random variables in compact metric spaces
- Statistical M-estimation and consistency in large deformable models for image warping
- Wasserstein barycenters over Riemannian manifolds
- Measurability of optimal transportation and strong coupling of martingale measures
- Statistical models for deformable templates in image and shape analysis
- Towards a Coherent Statistical Framework for Dense Deformable Template Estimation
- Title not available (Why is that?)
Cited In (19)
- Global Sensitivity Analysis and Wasserstein Spaces
- Linearized optimal transport on manifolds
- Simple approximative algorithms for free-support Wasserstein barycenters
- Barycenters for the Hellinger--Kantorovich Distance Over $\mathbb{R}^d$
- Procrustes metrics on covariance operators and optimal transportation of Gaussian processes
- Central limit theorem and bootstrap procedure for Wasserstein's variations with an application to structural relationships between distributions
- Distributionally robust portfolio maximization and marginal utility pricing in one period financial markets
- Elements of Statistical Inference in 2-Wasserstein Space
- Quantitative stability of barycenters in the Wasserstein space
- Stochastic approximation versus sample average approximation for Wasserstein barycenters
- Randomized Wasserstein Barycenter Computation: Resampling with Statistical Guarantees
- Existence and consistency of Wasserstein barycenters
- Title not available (Why is that?)
- Entropic Approximation of Wasserstein Gradient Flows
- Entropic-Wasserstein Barycenters: PDE Characterization, Regularity, and CLT
- \(W_2\) barycenters for radially related distributions
- Hellinger–Kantorovich barycenter between Dirac measures
- Gaussian processes with multidimensional distribution inputs via optimal transport and Hilbertian embedding
- Bayesian learning with 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)
