When OT meets MoM: Robust estimation of Wasserstein Distance

06/18/2020
by   Guillaume Staerman, et al.
0

Issued from Optimal Transport, the Wasserstein distance has gained importance in Machine Learning due to its appealing geometrical properties and the increasing availability of efficient approximations. In this work, we consider the problem of estimating the Wasserstein distance between two probability distributions when observations are polluted by outliers. To that end, we investigate how to leverage Medians of Means (MoM) estimators to robustify the estimation of Wasserstein distance. Exploiting the dual Kantorovitch formulation of Wasserstein distance, we introduce and discuss novel MoM-based robust estimators whose consistency is studied under a data contamination model and for which convergence rates are provided. These MoM estimators enable to make Wasserstein Generative Adversarial Network (WGAN) robust to outliers, as witnessed by an empirical study on two benchmarks CIFAR10 and Fashion MNIST. Eventually, we discuss how to combine MoM with the entropy-regularized approximation of the Wasserstein distance and propose a simple MoM-based re-weighting scheme that could be used in conjunction with the Sinkhorn algorithm.

READ FULL TEXT

page 8

page 18

research
01/16/2023

Theoretical and computational aspects of robust optimal transportation, with applications to statistics and machine learning

Optimal transport (OT) theory and the related p-Wasserstein distance (W_...
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
02/02/2023

Robust Estimation under the Wasserstein Distance

We study the problem of robust distribution estimation under the Wassers...
research
06/04/2019

Confidence Regions in Wasserstein Distributionally Robust Estimation

Wasserstein distributionally robust optimization (DRO) estimators are ob...
research
07/04/2023

Wasserstein medians: robustness, PDE characterization and numerics

We investigate the notion of Wasserstein median as an alternative to the...
research
08/13/2018

The Gromov-Wasserstein distance between networks and stable network invariants

We define a metric---the Network Gromov-Wasserstein distance---on weight...
research
02/09/2023

Outlier-Robust Gromov Wasserstein for Graph Data

Gromov Wasserstein (GW) distance is a powerful tool for comparing and al...

Please sign up or login with your details

Forgot password? Click here to reset