Convergence and finite sample approximations of entropic regularized Wasserstein distances in Gaussian and RKHS settings

DOI10.1142/S0219530522500142MaRDI QIDQ5889893zbMATH OpenWikidataFDO

Authors Hà Quang Minh

Publication date 27 April 2023

Published in Analysis and Applications (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2101.01429

zbMATH Keywords

entropic regularizationGaussian measuresreproducing kernel Hilbert spacesWasserstein distance

Mathematics Subject Classification ID

Set functions and measures and integrals in infinite-dimensional spaces (Wiener measure, Gaussian measure, etc.) (28C20) Hilbert spaces with reproducing kernels (= (proper) functional Hilbert spaces, including de Branges-Rovnyak and other structured spaces) (46E22) Optimal transportation (49Q22)

Recommendations

• Entropic regularization of Wasserstein distance between infinite-dimensional Gaussian measures and Gaussian processes
• Finite Sample Approximations of Exact and Entropic Wasserstein Distances Between Covariance Operators and Gaussian Processes
• Entropy-regularized 2-Wasserstein distance between Gaussian measures
• Inference for empirical Wasserstein distances on finite spaces
• Sharp asymptotic and finite-sample rates of convergence of empirical measures in Wasserstein distance
• Wasserstein distance on finite spaces: statistical inference and algorithms
• Convergence of the empirical measure in expected wasserstein distance: non-asymptotic explicit bounds in ℝ^d
• On the rate of convergence in Wasserstein distance of the empirical measure
• On the stochastic convergence of representations based on Wasserstein metrics

Cites work

• A class of Wasserstein metrics for probability distributions
• A kernel two-sample test
• A survey of the Schrödinger problem and some of its connections with optimal transport
• A well-conditioned estimator for large-dimensional covariance matrices
• Alpha Procrustes metrics between positive definite operators: a unifying formulation for the Bures-Wasserstein and Log-Euclidean/Log-Hilbert-Schmidt metrics
• Closedness of sum spaces and the generalized Schrödinger problem
• Convergence of the iterative proportional fitting procedure
• Entropic regularization of Wasserstein distance between infinite-dimensional Gaussian measures and Gaussian processes
• Entropy minimization, \(DAD\) problems, and doubly stochastic kernels
• Entropy-regularized 2-Wasserstein distance between Gaussian measures
• Finite Sample Approximations of Exact and Entropic Wasserstein Distances Between Covariance Operators and Gaussian Processes
• Free states of the canonical anticommutation relations
• How close is the sample covariance matrix to the actual covariance matrix?
• scientific article; zbMATH DE number 3863589 (Why is no real title available?)
• scientific article; zbMATH DE number 49190 (Why is no real title available?)
• scientific article; zbMATH DE number 3483022 (Why is no real title available?)
• scientific article; zbMATH DE number 1223843 (Why is no real title available?)
• I-divergence geometry of probability distributions and minimization problems
• Inequalities for the Schatten p-norm. V
• Learning theory estimates via integral operators and their approximations
• Limit laws of the empirical Wasserstein distance: Gaussian distributions
• Mean rates of convergence of empirical measures in the Wasserstein metric
• Note on the Schrödinger equation and \(I\)-projections
• Notes on infinite determinants of Hilbert space operators
• On a Formula for the L2 Wasserstein Metric between Measures on Euclidean and Hilbert Spaces
• On lower bounds for the \(L^ 2\)-Wasserstein metric in a Hilbert space
• On the mathematical foundations of learning
• On the optimal mapping of distributions
• On the rate of convergence in Wasserstein distance of the empirical measure
• On the scaling of multidimensional matrices
• Optimal rates of convergence for covariance matrix estimation
• Optimum bounds for the distributions of martingales in Banach spaces
• Procrustes metrics on covariance operators and optimal transportation of Gaussian processes
• Regularized estimation of large covariance matrices
• Sharp asymptotic and finite-sample rates of convergence of empirical measures in Wasserstein distance
• Support Vector Machines
• The distance between two random vectors wigh given dispersion matrices
• The Frechet distance between multivariate normal distributions
• The research program of stochastic deformation (with a view toward geometric mechanics)
• The Speed of Mean Glivenko-Cantelli Convergence
• Trace and Eigenvalue Inequalities for Ordinary and Hadamard Products of Positive Semidefinite Hermitian Matrices
• Wasserstein distance on finite spaces: statistical inference and algorithms

Cited in

(4)

• Finite Sample Approximations of Exact and Entropic Wasserstein Distances Between Covariance Operators and Gaussian Processes
• Universal consistency of Wasserstein k-NN classifier: a negative and some positive results
• Learning with centered reproducing kernels
• Infinite-dimensional distances and divergences between positive definite operators, Gaussian measures, and Gaussian processes

This page was built for publication: Convergence and finite sample approximations of entropic regularized Wasserstein distances in Gaussian and RKHS settings

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5889893)