Distributional Sliced-Wasserstein and Applications to Generative Modeling

02/18/2020
by   Khai Nguyen, et al.
4

Sliced-Wasserstein distance (SWD) and its variation, Max Sliced-Wasserstein distance (Max-SWD), have been widely used in the recent years due to their fast computation and scalability when the probability measures lie in very high dimension. However, these distances still have their weakness, SWD requires a lot of projection samples because it uses the uniform distribution to sample projecting directions, Max-SWD uses only one projection, causing it to lose a large amount of information. In this paper, we propose a novel distance that finds optimal penalized probability measure over the slices, which is named Distributional Sliced-Wasserstein distance (DSWD). We show that the DSWD is a generalization of both SWD and Max-SWD, and the proposed distance could be found by searching for the push-forward measure over a set of measures satisfying some certain constraints. Moreover, similar to SWD, we can extend Generalized Sliced-Wasserstein distance (GSWD) to Distributional Generalized Sliced-Wasserstein distance (DGSWD). Finally, we carry out extensive experiments to demonstrate the favorable generative modeling performances of our distances over the previous sliced-based distances in large-scale real datasets.

READ FULL TEXT

page 7

page 8

page 13

page 14

page 15

research
02/01/2019

Generalized Sliced Wasserstein Distances

The Wasserstein distance and its variations, e.g., the sliced-Wasserstei...
research
01/12/2023

Self-Attention Amortized Distributional Projection Optimization for Sliced Wasserstein Point-Cloud Reconstruction

Max sliced Wasserstein (Max-SW) distance has been widely known as a solu...
research
03/25/2022

Amortized Projection Optimization for Sliced Wasserstein Generative Models

Seeking informative projecting directions has been an important task in ...
research
01/10/2023

Markovian Sliced Wasserstein Distances: Beyond Independent Projections

Sliced Wasserstein (SW) distance suffers from redundant projections due ...
research
04/11/2019

Max-Sliced Wasserstein Distance and its use for GANs

Generative adversarial nets (GANs) and variational auto-encoders have si...
research
02/13/2018

Distributionally Robust Mean-Variance Portfolio Selection with Wasserstein Distances

We revisit Markowitz's mean-variance portfolio selection model by consid...
research
06/07/2022

Shedding a PAC-Bayesian Light on Adaptive Sliced-Wasserstein Distances

The Sliced-Wasserstein distance (SW) is a computationally efficient and ...

Please sign up or login with your details

Forgot password? Click here to reset