DeepAI AI Chat
Log In Sign Up

When Optimal Transport Meets Information Geometry

by   Gabriel Khan, et al.
Iowa State University of Science and Technology
University of Michigan

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.


page 1

page 2

page 3

page 4


Optimal transport and information geometry

Optimal transport and information geometry are both mathematical framewo...

Geometric Losses for Distributional Learning

Building upon recent advances in entropy-regularized optimal transport, ...

Theory and Approximate Solvers for Branched Optimal Transport with Multiple Sources

Branched Optimal Transport (BOT) is a generalization of optimal transpor...

Stability of Entropic Wasserstein Barycenters and application to random geometric graphs

As interest in graph data has grown in recent years, the computation of ...

Selective information exchange in collaborative clustering using regularized Optimal Transport

Collaborative learning has recently achieved very significant results. I...

Unlocking Slot Attention by Changing Optimal Transport Costs

Slot attention is a powerful method for object-centric modeling in image...

Accurate Baryon Acoustic Oscillations reconstruction via semi-discrete optimal transport

Optimal transport theory has recently reemerged as a vastly resourceful ...