Finite Sample Approximations of Exact and Entropic Wasserstein Distances Between Covariance Operators and Gaussian Processes
From MaRDI portal
(Redirected from Publication:5862898)
Abstract: This work studies finite sample approximations of the exact and entropic regularized Wasserstein distances between centered Gaussian processes and, more generally, covariance operators of functional random processes. We first show that these distances/divergences are fully represented by reproducing kernel Hilbert space (RKHS) covariance and cross-covariance operators associated with the corresponding covariance functions. Using this representation, we show that the Sinkhorn divergence between two centered Gaussian processes can be consistently and efficiently estimated from the divergence between their corresponding normalized finite-dimensional covariance matrices, or alternatively, their sample covariance operators. Consequently, this leads to a consistent and efficient algorithm for estimating the Sinkhorn divergence from finite samples generated by the two processes. For a fixed regularization parameter, the convergence rates are {it dimension-independent} and of the same order as those for the Hilbert-Schmidt distance. If at least one of the RKHS is finite-dimensional, we obtain a {it dimension-dependent} sample complexity for the exact Wasserstein distance between the Gaussian processes.
Recommendations
- Entropic regularization of Wasserstein distance between infinite-dimensional Gaussian measures and Gaussian processes
- Convergence and finite sample approximations of entropic regularized Wasserstein distances in Gaussian and RKHS settings
- Wasserstein distance on finite spaces: statistical inference and algorithms
- Riemannian distances between covariance operators and Gaussian processes
- Inference for empirical Wasserstein distances on finite spaces
- Gromov-Wasserstein distances between Gaussian distributions
- Entropy-regularized 2-Wasserstein distance between Gaussian measures
- Sharp asymptotic and finite-sample rates of convergence of empirical measures in Wasserstein distance
- Limit laws of the empirical Wasserstein distance: Gaussian distributions
- Precise limit in Wasserstein distance for conditional empirical measures of Dirichlet diffusion processes
Cites work
- A class of Wasserstein metrics for probability distributions
- A survey of the Schrödinger problem and some of its connections with optimal transport
- Bootstrap-based testing of equality of mean functions or equality of covariance operators for functional data
- Closedness of sum spaces and the generalized Schrödinger problem
- Computational optimal transport. With applications to data sciences
- Distances and inference for covariance operators
- Entropy minimization, \(DAD\) problems, and doubly stochastic kernels
- Free states of the canonical anticommutation relations
- Functional data analysis.
- Gaussian Processes and Gaussian Measures
- scientific article; zbMATH DE number 3863589 (Why is no real title available?)
- scientific article; zbMATH DE number 3820471 (Why is no real title available?)
- scientific article; zbMATH DE number 3483022 (Why is no real title available?)
- scientific article; zbMATH DE number 1909499 (Why is no real title available?)
- I-divergence geometry of probability distributions and minimization problems
- Inference for functional data with applications
- Learning theory estimates via integral operators and their approximations
- Mean rates of convergence of empirical measures in the Wasserstein metric
- Mercer theorem for RKHS on noncompact sets
- Nonparametric functional data analysis. Theory and practice.
- On a Formula for the L2 Wasserstein Metric between Measures on Euclidean and Hilbert Spaces
- On learning with integral operators
- 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
- Optimum bounds for the distributions of martingales in Banach spaces
- Procrustes metrics on covariance operators and optimal transportation of Gaussian processes
- Regularized divergences between covariance operators and Gaussian measures on Hilbert spaces
- Second-order comparison of Gaussian random functions and the geometry of DNA minicircles
- Sharp asymptotic and finite-sample rates of convergence of empirical measures in Wasserstein distance
- Some properties of Gaussian reproducing kernel Hilbert spaces and their implications for function approximation and learning theory
- Testing equality between several populations covariance operators
- Testing the equality of covariance operators in functional samples
- The distance between two random vectors wigh given dispersion matrices
- The Frechet distance between multivariate normal distributions
- The Speed of Mean Glivenko-Cantelli Convergence
Cited in
(8)- The entropy distance between the Wiener and stationary Gaussian measures
- Regularized divergences between covariance operators and Gaussian measures on Hilbert spaces
- Entropy-regularized 2-Wasserstein distance between Gaussian measures
- The nested Sinkhorn divergence to learn the nested distance
- Convergence and finite sample approximations of entropic regularized Wasserstein distances in Gaussian and RKHS settings
- Entropic regularization of Wasserstein distance between infinite-dimensional Gaussian measures and Gaussian processes
- Large sample theory for Bures-Wasserstein barycentres
- Infinite-dimensional distances and divergences between positive definite operators, Gaussian measures, and Gaussian processes
This page was built for publication: Finite Sample Approximations of Exact and Entropic Wasserstein Distances Between Covariance Operators and Gaussian Processes
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5862898)
