When Optimal Transport Meets Information Geometry

Abstract

Information geometry and optimal transport are two distinct geometric frameworks for modeling families of probability measures. During the recent years, there has been a surge of research endeavors that cut across these two areas and explore their links and interactions. This paper is intended to provide an (incomplete) survey of these works, including entropy-regularized transport, divergence functions arising from $c$-duality, density manifolds and transport information geometry, the para-Kähler and Kähler geometries underlying optimal transport and the regularity theory for its solutions. Some outstanding questions that would be of interest to audience of both these two disciplines are posed. Our piece also serves as an introduction to the Special Issue on Optimal Transport of the journal Information Geometry.

arXiv comment33 pages, 2 figures, to appear in Information Geometry

References in corpus (6)

• Near-linear time approximation algorithms for optimal transport via Sinkhorn iteration
• Optimal Entropy-Transport problems and a new Hellinger-Kantorovich distance between positive measures
• Special Geometry of Euclidean Supersymmetry I: Vector Multiplets
• On the Kähler Geometry of Certain Optimal Transport Problems
• A parabolic flow toward solutions of the optimal transportation problem on domains with boundary
• Tsallis and Rényi deformations linked via a new $\lambda$-duality

Cited by in corpus (2)

• Geometric thermodynamics for the Fokker-Planck equation: Stochastic thermodynamic links between information geometry and optimal transport
• Beyond Linear Response: Equivalence between Thermodynamic Geometry and Optimal Transport