CUED Publications database

Orthogonal Estimation of Wasserstein Distances

Rowland, M and Hron, J and Tang, Y and Choromanski, K and Sarlos, T and Weller, A Orthogonal Estimation of Wasserstein Distances. (Unpublished)

Full text not available from this repository.


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.

Item Type: Article
Uncontrolled Keywords: stat.ML stat.ML cs.LG
Divisions: Div F > Computational and Biological Learning
Depositing User: Cron Job
Date Deposited: 20 Mar 2019 20:04
Last Modified: 18 Feb 2021 18:14