Entropic Optimal Transport between Unbalanced Gaussian Measures has a Closed Form

Abstract

Although optimal transport (OT) problems admit closed form solutions in a very few notable cases, e.g. in 1D or between Gaussians, these closed forms have proved extremely fecund for practitioners to define tools inspired from the OT geometry. On the other hand, the numerical resolution of OT problems using entropic regularization has given rise to many applications, but because there are no known closed-form solutions for entropic regularized OT problems, these approaches are mostly algorithmic, not informed by elegant closed forms. In this paper, we propose to fill the void at the intersection between these two schools of thought in OT by proving that the entropy-regularized optimal transport problem between two Gaussian measures admits a closed form. Contrary to the unregularized case, for which the explicit form is given by the Wasserstein-Bures distance, the closed form we obtain is differentiable everywhere, even for Gaussians with degenerate covariance matrices. We obtain this closed form solution by solving the fixed-point equation behind Sinkhorn's algorithm, the default method for computing entropic regularized OT. Remarkably, this approach extends to the generalized unbalanced case -- where Gaussian measures are scaled by positive constants. This extension leads to a closed form expression for unbalanced Gaussians as well, and highlights the mass transportation / destruction trade-off seen in unbalanced optimal transport. Moreover, in both settings, we show that the optimal transportation plans are (scaled) Gaussians and provide analytical formulas of their parameters. These formulas constitute the first non-trivial closed forms for entropy-regularized optimal transport, thus providing a ground truth for the analysis of entropic OT and Sinkhorn's algorithm.

References in corpus (11)

• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
• Learning with a Wasserstein Loss
• Sample Complexity of Sinkhorn divergences
• Interpolating between Optimal Transport and MMD using Sinkhorn Divergences
• Subspace Robust Wasserstein Distances
• Generalizing Point Embeddings using the Wasserstein Space of Elliptical Distributions
• Sinkhorn Divergences for Unbalanced Optimal Transport
• Statistical bounds for entropic optimal transport: sample complexity and the central limit theorem
• Wasserstein Riemannian Geometry of Positive Definite Matrices
• Debiased Sinkhorn barycenters
• The statistical effect of entropic regularization in optimal transportation

Cited by in corpus (15)

• Faster Wasserstein Distance Estimation with the Sinkhorn Divergence
• Unbalanced Multi-Marginal Optimal Transport
• The statistical effect of entropic regularization in optimal transportation
• Entropic regularization of Wasserstein distance between infinite-dimensional Gaussian measures and Gaussian processes
• Estimating Barycenters of Measures in High Dimensions
• Learning Cost Functions for Optimal Transport
• Score-based Generative Neural Networks for Large-Scale Optimal Transport
• Averaging on the Bures-Wasserstein manifold: dimension-free convergence of gradient descent
• Sinkhorn Natural Gradient for Generative Models
• Entropic Gromov-Wasserstein between Gaussian Distributions
• Online Sinkhorn: Optimal Transport distances from sample streams
• Estimating 2-Sinkhorn Divergence between Gaussian Processes from Finite-Dimensional Marginals
• Convergence and finite sample approximations of entropic regularized Wasserstein distances in Gaussian and RKHS settings
• Schrödinger encounters Fisher and Rao: a survey
• Generalized Talagrand Inequality for Sinkhorn Distance using Entropy Power Inequality