Entropy-regularized 2-Wasserstein distance between Gaussian measures
From MaRDI portal
Abstract: Gaussian distributions are plentiful in applications dealing in uncertainty quantification and diffusivity. They furthermore stand as important special cases for frameworks providing geometries for probability measures, as the resulting geometry on Gaussians is often expressible in closed-form under the frameworks. In this work, we study the Gaussian geometry under the entropy-regularized 2-Wasserstein distance, by providing closed-form solutions for the distance and interpolations between elements. Furthermore, we provide a fixed-point characterization of a population barycenter when restricted to the manifold of Gaussians, which allows computations through the fixed-point iteration algorithm. As a consequence, the results yield closed-form expressions for the 2-Sinkhorn divergence. As the geometries change by varying the regularization magnitude, we study the limiting cases of vanishing and infinite magnitudes, reconfirming well-known results on the limits of the Sinkhorn divergence. Finally, we illustrate the resulting geometries with a numerical study.
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
- Wasserstein geometry of Gaussian measures
- Limit laws of the empirical Wasserstein distance: Gaussian distributions
- On Wasserstein geometry of the space of Gaussian measures
Cites work
- A class of Wasserstein metrics for probability distributions
- A convexity principle for interacting gases
- A fixed-point approach to barycenters in Wasserstein space
- A Riemannian framework for tensor computing
- A survey of the Schrödinger problem and some of its connections with optimal transport
- About the analogy between optimal transport and minimal entropy
- An optimal transport approach for the Schrödinger bridge problem and convergence of Sinkhorn algorithm
- Barycenters in the Wasserstein space
- Benamou-Brenier and duality formulas for the entropic cost on \(\mathsf{RCD}^*(K,N)\) spaces
- Closedness of sum spaces and the generalized Schrödinger problem
- Computational optimal transport. With applications to data sciences
- Convergence of the iterative proportional fitting procedure
- Designing a boosted classifier on Riemannian manifolds
- Entropy minimization, \(DAD\) problems, and doubly stochastic kernels
- Exploration of balanced metrics on symmetric positive definite matrices
- Geometric Means in a Novel Vector Space Structure on Symmetric Positive‐Definite Matrices
- Gradient flows in metric spaces and in the space of probability measures
- I-divergence geometry of probability distributions and minimization problems
- Infinite-dimensional log-determinant divergences between positive definite trace class operators
- Information geometry
- Information geometry and its applications
- Information geometry connecting Wasserstein distance and Kullback-Leibler divergence via the entropy-relaxed transportation problem
- Integral Probability Metrics and Their Generating Classes of Functions
- Iterative Bregman projections for regularized transportation problems
- Log-determinant divergences revisited: alpha-beta and gamma log-det divergences
- Means of Hermitian positive-definite matrices based on the log-determinant \(\alpha\)-divergence function
- Multi-marginal entropy-transport with repulsive cost
- Non-Euclidean statistics for covariance matrices, with applications to diffusion tensor imaging
- Nonpositive curvature: A geometrical approach to Hilbert-Schmidt operators
- Note on the Schrödinger equation and \(I\)-projections
- On the optimal mapping of distributions
- On the relation between optimal transport and Schrödinger bridges: a stochastic control viewpoint
- On the scaling of multidimensional matrices
- Optimal Steering of a Linear Stochastic System to a Final Probability Distribution, Part I
- Optimal Transport
- Penalization of barycenters in the Wasserstein space
- Procrustes metrics on covariance operators and optimal transportation of Gaussian processes
- Regularized barycenters in the Wasserstein space
- Second order differentiation formula on \(\mathsf{RCD}(K,N)\) spaces
- Sharp asymptotic and finite-sample rates of convergence of empirical measures in Wasserstein distance
- The distance between two random vectors wigh given dispersion matrices
- The earth mover's distance as a metric for image retrieval
- The Frechet distance between multivariate normal distributions
- The research program of stochastic deformation (with a view toward geometric mechanics)
- Wasserstein distance on finite spaces: statistical inference and algorithms
- Wasserstein geometry of Gaussian measures
- Wasserstein Riemannian geometry of Gaussian densities
Cited in
(14)- The entropy distance between the Wiener and stationary Gaussian measures
- Asymptotics of smoothed Wasserstein distances
- When optimal transport meets information geometry
- Gromov-Wasserstein distances between Gaussian distributions
- Finite Sample Approximations of Exact and Entropic Wasserstein Distances Between Covariance Operators and Gaussian Processes
- 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
- An entropic generalization of Caffarelli's contraction theorem via covariance inequalities
- An Improved Central Limit Theorem and Fast Convergence Rates for Entropic Transportation Costs
- Bayesian learning with Wasserstein barycenters
- Entropic adapted Wasserstein distance on Gaussians
- The multiscale nonlocal-in-time Schrödinger bridge problem
- Stochastic gradient descent for barycenters in Wasserstein space
- A uniform rate of convergence for the entropic potentials in the quadratic euclidean setting
This page was built for publication: Entropy-regularized 2-Wasserstein distance between Gaussian measures
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2154664)
