Orthogonal Estimation of Wasserstein Distances

international conference on artificial intelligence and statistics, 2019.

Cited by: 8|Views60
EI

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...More

Code:

Data:

Your rating :
0

 

Tags
Comments