Multi-Marginal Optimal Transport Defines a Generalized Metric

01/29/2020
by   Liang Mi, et al.
3

We prove that the multi-marginal optimal transport (MMOT) problem defines a generalized metric. In addition, we prove that the distance induced by MMOT satisfies a generalized triangle inequality that, to leading order, cannot be improved.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/03/2022

Transport type metrics on the space of probability measures involving singular base measures

We develop the theory of a metric, which we call the ν-based Wasserstein...
research
08/22/2022

Information-Theoretic Equivalence of Entropic Multi-Marginal Optimal Transport: A Theory for Multi-Agent Communication

In this paper, we propose our information-theoretic equivalence of entro...
research
07/29/2019

Diffusion Hypercontractivity via Generalized Density Manifold

We prove a one-parameter family of diffusion hypercontractivity and pres...
research
02/14/2021

Sliced Multi-Marginal Optimal Transport

We study multi-marginal optimal transport, a generalization of optimal t...
research
02/24/2020

Computing Kantorovich distance with a MCMC of moves

In Optimal Transport (OT) on a finite metric space, one defines a distan...
research
09/17/2021

Generalized Talagrand Inequality for Sinkhorn Distance using Entropy Power Inequality

In this paper, we study the connection between entropic optimal transpor...
research
06/26/2019

Hierarchical Optimal Transport for Document Representation

The ability to measure similarity between documents enables intelligent ...

Please sign up or login with your details

Forgot password? Click here to reset