Wasserstein Iterative Networks for Barycenter Estimation

01/28/2022
by   Alexander Korotin, et al.
0

Wasserstein barycenters have become popular due to their ability to represent the average of probability measures in a geometrically meaningful way. In this paper, we present an algorithm to approximate the Wasserstein-2 barycenters of continuous measures via a generative model. Previous approaches rely on regularization (entropic/quadratic) which introduces bias or on input convex neural networks which are not expressive enough for large-scale tasks. In contrast, our algorithm does not introduce bias and allows using arbitrary neural networks. In addition, based on the celebrity faces dataset, we construct Ave, celeba! dataset which can be used for quantitative evaluation of barycenter algorithms by using standard metrics of generative models such as FID.

READ FULL TEXT

page 6

page 7

page 8

page 16

page 18

page 19

page 20

page 21

research
02/02/2021

Continuous Wasserstein-2 Barycenter Estimation without Minimax Optimization

Wasserstein barycenters provide a geometric notion of the weighted avera...
research
07/08/2020

Scalable Computations of Wasserstein Barycenter via Input Convex Neural Networks

Wasserstein Barycenter is a principled approach to represent the weighte...
research
06/11/2019

Asymptotic Guarantees for Learning Generative Models with the Sliced-Wasserstein Distance

Minimum expected distance estimation (MEDE) algorithms have been widely ...
research
08/15/2019

Using Wasserstein-2 regularization to ensure fair decisions with Neural-Network classifiers

In this paper, we propose a new method to build fair Neural-Network clas...
research
01/08/2017

A Framework for Wasserstein-1-Type Metrics

We propose a unifying framework for generalising the Wasserstein-1 metri...
research
03/25/2022

Amortized Projection Optimization for Sliced Wasserstein Generative Models

Seeking informative projecting directions has been an important task in ...
research
03/05/2020

Regularized Variational Data Assimilation for Bias Treatment using the Wasserstein Metric

This paper presents a new variational data assimilation (VDA) approach f...

Please sign up or login with your details

Forgot password? Click here to reset