Unbalanced Multi-Marginal Optimal Transport

Abstract

Entropy regularized optimal transport and its multi-marginal generalization have attracted increasing attention in various applications, in particular due to efficient Sinkhorn-like algorithms for computing optimal transport plans. However, it is often desirable that the marginals of the optimal transport plan do not match the given measures exactly, which led to the introduction of the so-called unbalanced optimal transport. Since unbalanced methods were not examined for the multi-marginal setting so far, we address this topic in the present paper. More precisely, we introduce the unbalanced multi-marginal optimal transport problem and its dual, and show that a unique optimal transport plan exists under mild assumptions. Further, we generalize the Sinkhorn algorithm for regularized unbalanced optimal transport to the multi-marginal setting and prove its convergence. If the cost function decouples according to a tree, the iterates can be computed efficiently. At the end, we discuss three applications of our framework, namely two barycenter problems and a transfer operator approach, where we establish a relation between the barycenter problem and the multi-marginal optimal transport with an appropriate tree-structured cost function.

References in corpus (13)

• Fast Computation of Wasserstein Barycenters
• Learning with a Wasserstein Loss
• Data-driven model reduction and transfer operator approximation
• Optimal Entropy-Transport problems and a new Hellinger-Kantorovich distance between positive measures
• An analytic framework for identifying finite-time coherent sets in time-dependent dynamical systems
• Entropic regularization of continuous optimal transport problems
• Sinkhorn Divergences for Unbalanced Optimal Transport
• Entropic Optimal Transport between Unbalanced Gaussian Measures has a Closed Form
• Debiased Sinkhorn barycenters
• Barycenters for the Hellinger--Kantorovich distance over ${\mathbb{R}}^d$
• Transfer Operators from Optimal Transport Plans for Coherent Set Detection
• Entropic regularization of Wasserstein distance between infinite-dimensional Gaussian measures and Gaussian processes
• Sliced Multi-Marginal Optimal Transport

Cited by in corpus (7)

• Accelerating the Sinkhorn algorithm for sparse multi-marginal optimal transport by fast Fourier transforms
• Sliced Optimal Transport on the Sphere
• Low-rank tensor approximations for solving multi-marginal optimal transport problems
• Parallelly Sliced Optimal Transport on Spheres and on the Rotation Group
• Definition, detection, and tracking of persistent structures in atmospheric flows
• Constrained Hellinger-Kantorovich barycenters: least-cost soft and conic multi-marginal formulations
• HOT-POT: Optimal Transport for Sparse Stereo Matching