Entropy-regularized optimal transport on multivariate normal and q-normal distributions

12/19/2020
by   Qijun Tong, et al.
0

Distance and divergence of the probability measures play a central role in statistics, machine learning, and many other related fields. The Wasserstein distance has received much attention in recent years because of its distinctions from other distances or divergences. Although computing the Wasserstein distance is costly, entropy-regularized optimal transport was proposed to approximate the Wasserstein distance computationally efficiently. The purpose of this study is to understand the theoretical aspect of entropy-regularized optimal transport. In this paper, we focus on entropy-regularized optimal transport on multivariate normal distributions and q-normal distributions. We obtain the explicit form of the entropy-regularized optimal transport cost on multivariate normal and q-normal distributions; this provides a perspective to understand the effect of entropy regularization, which was previously known only experimentally. Furthermore, we demonstrate how the Wasserstein distance, optimal coupling, geometric structure, and statistical efficiency are affected by entropy regularization in some experiments.

READ FULL TEXT
research
08/30/2022

Convergence Rates for Regularized Optimal Transport via Quantization

We study the convergence of divergence-regularized optimal transport as ...
research
10/13/2022

On the potential benefits of entropic regularization for smoothing Wasserstein estimators

This paper is focused on the study of entropic regularization in optimal...
research
01/29/2020

Domain decomposition for entropy regularized optimal transport

We study Benamou's domain decomposition algorithm for optimal transport ...
research
02/10/2020

Regularized Optimal Transport is Ground Cost Adversarial

Regularizing Wasserstein distances has proved to be the key in the recen...
research
02/12/2018

A Fast Proximal Point Method for Wasserstein Distance

Wasserstein distance plays increasingly important roles in machine learn...
research
06/09/2020

The statistical effect of entropic regularization in optimal transportation

We propose to tackle the problem of understanding the effect of regulari...
research
04/18/2023

Sliced Optimal Transport on the Sphere

Sliced optimal transport reduces optimal transport on multi-dimensional ...

Please sign up or login with your details

Forgot password? Click here to reset