Orthogonal Estimation of Wasserstein Distances
Abstract
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.
Cite
Text
Rowland et al. "Orthogonal Estimation of Wasserstein Distances." Artificial Intelligence and Statistics, 2019.Markdown
[Rowland et al. "Orthogonal Estimation of Wasserstein Distances." Artificial Intelligence and Statistics, 2019.](https://mlanthology.org/aistats/2019/rowland2019aistats-orthogonal/)BibTeX
@inproceedings{rowland2019aistats-orthogonal,
title = {{Orthogonal Estimation of Wasserstein Distances}},
author = {Rowland, Mark and Hron, Jiri and Tang, Yunhao and Choromanski, Krzysztof and Sarlos, Tamas and Weller, Adrian},
booktitle = {Artificial Intelligence and Statistics},
year = {2019},
pages = {186-195},
volume = {89},
url = {https://mlanthology.org/aistats/2019/rowland2019aistats-orthogonal/}
}