Empirical optimal transport on countable metric spaces: distributional limits and statistical applications
From MaRDI portal
Publication:2286450
Limit theorems for vector-valued random variables (infinite-dimensional case) (60B12) Central limit and other weak theorems (60F05) Asymptotic distribution theory in statistics (62E20) Nonparametric hypothesis testing (62G10) Special problems of linear programming (transportation, multi-index, data envelopment analysis, etc.) (90C08) Sensitivity, stability, parametric optimization (90C31)
Abstract: We derive distributional limits for empirical transport distances between probability measures supported on countable sets. Our approach is based on sensitivity analysis of optimal values of infinite dimensional mathematical programs and a delta method for non-linear derivatives. A careful calibration of the norm on the space of probability measures is needed in order to combine differentiability and weak convergence of the underlying empirical process. Based on this we provide a sufficient and necessary condition for the underlying distribution on the countable metric space for such a distributional limit to hold. We give an explicit form of the limiting distribution for ultra-metric spaces. Finally, we apply our findings to optimal transport based inference in large scale problems. An application to nanoscale microscopy is given.
Recommendations
- Empirical regularized optimal transport: statistical theory and applications
- Wasserstein distance on finite spaces: statistical inference and algorithms
- Inference for empirical Wasserstein distances on finite spaces
- On the Rate of Convergence of Empirical Measures in ∞-transportation Distance
- Central limit theorems for entropy-regularized optimal transport on finite spaces and statistical applications
Cites work
- A Faster Strongly Polynomial Minimum Cost Flow Algorithm
- A new algorithm for the assignment problem
- A Note on Asymptotic Joint Normality
- A sparse multiscale algorithm for dense optimal transport
- A weighted approximation approach to the study of the empirical Wasserstein distance
- Amplitude and phase variation of point processes
- An empirical central limit theorem in L^1 for stationary sequences
- Asymptotic analysis of stochastic programs
- Asymptotics for L₂ functionals of the empirical quantile process, with applications to tests of fit based on weighted Wasserstein distances
- Auction algorithms for network flow problems: A tutorial introduction
- Behavior of the Wasserstein distance between the empirical and the marginal distributions of stationary \(\alpha\)-dependent sequences
- Central limit theorem and convergence to stable laws in Mallows distance
- Central limit theorems for empirical transportation cost in general dimension
- Central limit theorems for the Wasserstein distance between the empirical and the true distributions
- Contributions of empirical and quantile processes to the asymptotic theory of goodness-of-fit tests. (With comments)
- Convolutional Wasserstein distances: efficient optimal transportation on geometric domains
- Degeneracy in transportation problems
- Drift estimation in sparse sequential dynamic imaging, with application to nanoscale fluorescence microscopy
- Error bounds for Metropolis-Hastings algorithms applied to perturbations of Gaussian measures in high dimensions
- scientific article; zbMATH DE number 3134565 (Why is no real title available?)
- scientific article; zbMATH DE number 5604036 (Why is no real title available?)
- scientific article; zbMATH DE number 3490255 (Why is no real title available?)
- scientific article; zbMATH DE number 3605665 (Why is no real title available?)
- scientific article; zbMATH DE number 1220667 (Why is no real title available?)
- scientific article; zbMATH DE number 699478 (Why is no real title available?)
- scientific article; zbMATH DE number 1502618 (Why is no real title available?)
- scientific article; zbMATH DE number 1909499 (Why is no real title available?)
- scientific article; zbMATH DE number 3429908 (Why is no real title available?)
- scientific article; zbMATH DE number 3294139 (Why is no real title available?)
- scientific article; zbMATH DE number 3413294 (Why is no real title available?)
- Inference for empirical Wasserstein distances on finite spaces
- Limit laws of the empirical Wasserstein distance: Gaussian distributions
- Linear and nonlinear programming.
- Mass transportation problems. Vol. 1: Theory. Vol. 2: Applications
- Matching random samples in many dimensions
- Mean rates of convergence of empirical measures in the Wasserstein metric
- Nonparametric Validation of Similar Distributions and Assessment of Goodness of Fit
- On concepts of directional differentiability
- On Hadamard differentiability in k-sample semiparametric models -- with applications to the assessment of structural relationships
- On nondifferentiable functions and the bootstrap
- On optimal matchings
- On the mean speed of convergence of empirical and occupation measures in Wasserstein distance
- On the rate of convergence in Wasserstein distance of the empirical measure
- One-dimensional empirical measures, order statistics, and Kantorovich transport distances
- Optimal Transport
- Perturbation theory for Markov chains via Wasserstein distance
- Sharp asymptotic and finite-sample rates of convergence of empirical measures in Wasserstein distance
- Sliced and Radon Wasserstein barycenters of measures
- Some asymptotic theory for the bootstrap
- Stein's method and point process approximation
- Stein's method and Poisson process approximation for a class of Wasserstein metrics
- Tests of goodness of fit based on the L₂-Wasserstein distance
- The earth mover's distance as a metric for image retrieval
- The phylogenetic Kantorovich-Rubinstein metric for environmental sequence samples
- The transportation cost from the uniform measure to the empirical measure in dimension \(\geq 3\)
Cited in
(28)- Fréchet means and Procrustes analysis in Wasserstein space
- Multivariate goodness-of-fit tests based on Wasserstein distance
- Measuring dependence between random vectors via optimal transport
- Tackling algorithmic bias in neural-network classifiers using Wasserstein-2 regularization
- Likelihood estimation of sparse topic distributions in topic models and its applications to Wasserstein document distance calculations
- Minimax confidence intervals for the sliced Wasserstein distance
- Limit laws for empirical optimal solutions in random linear programs
- Central limit theorems for entropy-regularized optimal transport on finite spaces and statistical applications
- Empirical regularized optimal transport: statistical theory and applications
- Sharp convergence rates for empirical optimal transport with smooth costs
- Limit distributions and sensitivity analysis for empirical entropic optimal transport on countable spaces
- An Improved Central Limit Theorem and Fast Convergence Rates for Entropic Transportation Costs
- Distribution of Distances based Object Matching: Asymptotic Inference
- Central limit theorems for semi-discrete Wasserstein distances
- Asymptotics for Strassen's optimal transport problem
- Uniform confidence band for optimal transport map on one-dimensional data
- Asymptotics of discrete Schrödinger bridges via chaos decomposition
- A unifying approach to distributional limits for empirical optimal transport
- Limit distribution theory for smooth \(p\)-Wasserstein distances
- Central limit theorems for general transportation costs
- Plugin estimation of smooth optimal transport maps
- Gromov-Wasserstein distances: entropic regularization, duality and sample complexity
- Empirical optimal transport under estimated costs: distributional limits and statistical applications
- Statistical inference with regularized optimal transport
- Empirical martingale projections via the adapted Wasserstein distance
- k-sample inference via multimarginal optimal transport
- On the uniqueness of Kantorovich potentials
- Estimation and inference for the Wasserstein distance between mixing measures in topic models
This page was built for publication: Empirical optimal transport on countable metric spaces: distributional limits and statistical applications
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2286450)
