Central limit theorems for entropy-regularized optimal transport on finite spaces and statistical applications
From MaRDI portal
Publication:2283574
Abstract: The notion of entropy-regularized optimal transport, also known as Sinkhorn divergence, has recently gained popularity in machine learning and statistics, as it makes feasible the use of smoothed optimal transportation distances for data analysis. The Sinkhorn divergence allows the fast computation of an entropically regularized Wasserstein distance between two probability distributions supported on a finite metric space of (possibly) high-dimension. For data sampled from one or two unknown probability distributions, we derive the distributional limits of the empirical Sinkhorn divergence and its centered version (Sinkhorn loss). We also propose a bootstrap procedure which allows to obtain new test statistics for measuring the discrepancies between multivariate probability distributions. Our work is inspired by the results of Sommerfeld and Munk (2016) on the asymptotic distribution of empirical Wasserstein distance on finite space using unregularized transportation costs. Incidentally we also analyze the asymptotic distribution of entropy-regularized Wasserstein distances when the regularization parameter tends to zero. Simulated and real datasets are used to illustrate our approach.
Recommendations
- An Improved Central Limit Theorem and Fast Convergence Rates for Entropic Transportation Costs
- Optimal transportation-entropy inequalities for several usual distributions on \(\mathbb R\)
- Empirical optimal transport on countable metric spaces: distributional limits and statistical applications
- Empirical regularized optimal transport: statistical theory and applications
- Asymptotic distribution and convergence rates of stochastic algorithms for entropic optimal transportation between probability measures
- Entropy inequalities for stable densities and strengthened central limit theorems
- Transport-entropy inequalities and deviation estimates for stochastic approximation schemes
- Entropic optimal transport: geometry and large deviations
- A note on the regularity of optimal-transport-based center-outward distribution and quantile functions
- Entropic regularization of continuous optimal transport problems
Cites work
- scientific article; zbMATH DE number 1807400 (Why is no real title available?)
- scientific article; zbMATH DE number 708500 (Why is no real title available?)
- scientific article; zbMATH DE number 2038320 (Why is no real title available?)
- scientific article; zbMATH DE number 1909499 (Why is no real title available?)
- scientific article; zbMATH DE number 2107836 (Why is no real title available?)
- A smoothed dual approach for variational Wasserstein problems
- Asymptotic analysis of objectives based on Fisher information in active learning
- Asymptotics for \(L_2\) functionals of the empirical quantile process, with applications to tests of fit based on weighted Wasserstein distances
- Central limit theorems for empirical transportation cost in general dimension
- Convergence of latent mixing measures in finite and infinite mixture models
- Convex color image segmentation with optimal transport distances
- Convolutional Wasserstein distances: efficient optimal transportation on geometric domains
- Data-driven regularization of Wasserstein barycenters with an application to multivariate density registration
- Empirical regularized optimal transport: statistical theory and applications
- Fast Discrete Distribution Clustering Using Wasserstein Barycenter With Sparse Support
- Geodesic PCA in the Wasserstein space by convex PCA
- Geodesic PCA versus Log-PCA of Histograms in the Wasserstein Space
- Inference for empirical Wasserstein distances on finite spaces
- Inference on functionals under first order degeneracy
- Inverses of \(2\times 2\) block matrices
- Limit laws of the empirical Wasserstein distance: Gaussian distributions
- On Hadamard differentiability in \(k\)-sample semiparametric models -- with applications to the assessment of structural relationships
- Tests of goodness of fit based on the \(L_2\)-Wasserstein distance
- Wasserstein dictionary learning: optimal transport-based unsupervised nonlinear dictionary learning
- Weak convergence and empirical processes. With applications to statistics
Cited in
(20)- Limit distribution theory for smooth \(p\)-Wasserstein distances
- Gromov-Wasserstein distances: entropic regularization, duality and sample complexity
- Minimax estimation of smooth optimal transport maps
- Empirical optimal transport on countable metric spaces: distributional limits and statistical applications
- Scaling positive random matrices: concentration and asymptotic convergence
- Projection-based techniques for high-dimensional optimal transport problems
- Limit theorems for entropic optimal transport maps and Sinkhorn divergence
- Uniform confidence band for optimal transport map on one-dimensional data
- From optimal transport to discrepancy
- Statistical inference with regularized optimal transport
- Asymptotic distribution and convergence rates of stochastic algorithms for entropic optimal transportation between probability measures
- Empirical regularized optimal transport: statistical theory and applications
- The nested Sinkhorn divergence to learn the nested distance
- A central limit theorem for Lp transportation cost on the real line with application to fairness assessment in machine learning
- An Improved Central Limit Theorem and Fast Convergence Rates for Entropic Transportation Costs
- Asymptotics of discrete Schrödinger bridges via chaos decomposition
- Limit distributions and sensitivity analysis for empirical entropic optimal transport on countable spaces
- Estimation of Wasserstein distances in the spiked transport model
- Empirical optimal transport under estimated costs: distributional limits and statistical applications
- Stochastic approximation versus sample average approximation for Wasserstein barycenters
This page was built for publication: Central limit theorems for entropy-regularized optimal transport on finite spaces and statistical applications
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2283574)
