Augmented Sliced Wasserstein Distances

06/15/2020
by   Xiongjie Chen, et al.
0

While theoretically appealing, the application of the Wasserstein distance to large-scale machine learning problems has been hampered by its prohibitive computational cost. The sliced Wasserstein distance and its variants improve the computational efficiency through random projection, yet they suffer from low projection efficiency because the majority of projections result in trivially small values. In this work, we propose a new family of distance metrics, called augmented sliced Wasserstein distances (ASWDs), constructed by first mapping samples to higher-dimensional hypersurfaces parameterized by neural networks. It is derived from a key observation that (random) linear projections of samples residing on these hypersurfaces would translate to much more flexible projections in the original sample space, so they can capture complex structures of the data distribution. We show that the hypersurfaces can be optimized by gradient ascent efficiently. We provide the condition under which the ASWD is a valid metric and show that this can be obtained by an injective neural network architecture. Numerical results demonstrate that the ASWD significantly outperforms other Wasserstein variants for both synthetic and real-world problems.

READ FULL TEXT
research
02/11/2022

Inference for Projection-Based Wasserstein Distances on Finite Spaces

The Wasserstein distance is a distance between two probability distribut...
research
06/01/2022

Distributional Convergence of the Sliced Wasserstein Process

Motivated by the statistical and computational challenges of computing W...
research
06/29/2021

Fast Approximation of the Sliced-Wasserstein Distance Using Concentration of Random Projections

The Sliced-Wasserstein distance (SW) is being increasingly used in machi...
research
03/09/2019

Orthogonal Estimation of Wasserstein Distances

Wasserstein distances are increasingly used in a wide variety of applica...
research
05/30/2022

Hilbert Curve Projection Distance for Distribution Comparison

Distribution comparison plays a central role in many machine learning ta...
research
03/15/2012

Approximating Higher-Order Distances Using Random Projections

We provide a simple method and relevant theoretical analysis for efficie...
research
05/16/2022

Wasserstein t-SNE

Scientific datasets often have hierarchical structure: for example, in s...

Please sign up or login with your details

Forgot password? Click here to reset