A Framework for Wasserstein-1-Type Metrics

01/08/2017
by   Bernhard Schmitzer, et al.
0

We propose a unifying framework for generalising the Wasserstein-1 metric to a discrepancy measure between nonnegative measures of different mass. This generalization inherits the convexity and computational efficiency from the Wasserstein-1 metric, and it includes several previous approaches from the literature as special cases. For various specific instances of the generalized Wasserstein-1 metric we furthermore demonstrate their usefulness in applications by numerical experiments.

READ FULL TEXT

page 30

page 31

page 32

page 33

page 34

page 37

research
08/27/2019

On the Minimax Optimality of Estimating the Wasserstein Metric

We study the minimax optimal rate for estimating the Wasserstein-1 metri...
research
02/10/2019

(q,p)-Wasserstein GANs: Comparing Ground Metrics for Wasserstein GANs

Generative Adversial Networks (GANs) have made a major impact in compute...
research
11/01/2020

Distances between probability distributions of different dimensions

Comparing probability distributions is an indispensable and ubiquitous t...
research
10/10/2019

Computationally Efficient Tree Variants of Gromov-Wasserstein

We propose two novel variants of Gromov-Wasserstein (GW) between probabi...
research
10/20/2020

Wasserstein K-Means for Clustering Tomographic Projections

Motivated by the 2D class averaging problem in single-particle cryo-elec...
research
06/22/2022

Hellinger-Kantorovich barycenter between Dirac measures

The Hellinger-Kantorovich (HK) distance is an unbalanced extension of th...
research
01/28/2022

Wasserstein Iterative Networks for Barycenter Estimation

Wasserstein barycenters have become popular due to their ability to repr...

Please sign up or login with your details

Forgot password? Click here to reset