Orthogonal Estimation of Wasserstein Distances

03/09/2019
by   Mark Rowland, et al.
7

Wasserstein distances are increasingly used in a wide variety of applications in machine learning. Sliced Wasserstein distances form an important subclass which may be estimated efficiently through one-dimensional sorting operations. In this paper, we propose a new variant of sliced Wasserstein distance, study the use of orthogonal coupling in Monte Carlo estimation of Wasserstein distances and draw connections with stratified sampling, and evaluate our approaches experimentally in a range of large-scale experiments in generative modelling and reinforcement learning.

READ FULL TEXT
research
02/01/2019

Generalized Sliced Wasserstein Distances

The Wasserstein distance and its variations, e.g., the sliced-Wasserstei...
research
12/12/2018

Massively scalable Sinkhorn distances via the Nyström method

The Sinkhorn distance, a variant of the Wasserstein distance with entrop...
research
04/02/2018

On the Computation of Kantorovich-Wasserstein Distances between 2D-Histograms by Uncapacitated Minimum Cost Flows

In this work, we present a method to compute the Kantorovich distance, t...
research
10/26/2017

A Central Limit Theorem for Wasserstein type distances between two different laws

This article is dedicated to the estimation of Wasserstein distances and...
research
06/15/2020

Augmented Sliced Wasserstein Distances

While theoretically appealing, the application of the Wasserstein distan...
research
03/22/2022

Bounds on Wasserstein distances between continuous distributions using independent samples

The plug-in estimator of the Wasserstein distance is known to be conserv...
research
08/02/2023

Wasserstein Diversity-Enriched Regularizer for Hierarchical Reinforcement Learning

Hierarchical reinforcement learning composites subpolicies in different ...

Please sign up or login with your details

Forgot password? Click here to reset