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

01/16/2023
by   Yiming Ma, et al.
0

Optimal transport (OT) theory and the related p-Wasserstein distance (W_p, p≥ 1) are popular tools in statistics and machine learning. Recent studies have been remarking that inference based on OT and on W_p is sensitive to outliers. To cope with this issue, we work on a robust version of the primal OT problem (ROBOT) and show that it defines a robust version of W_1, called robust Wasserstein distance, which is able to downweight the impact of outliers. We study properties of this novel distance and use it to define minimum distance estimators. Our novel estimators do not impose any moment restrictions: this allows us to extend the use of OT methods to inference on heavy-tailed distributions. We also provide statistical guarantees of the proposed estimators. Moreover, we derive the dual form of the ROBOT and illustrate its applicability to machine learning. Numerical exercises (see also the supplementary material) provide evidence of the benefits yielded by our methods.

READ FULL TEXT
research
06/18/2020

When OT meets MoM: Robust estimation of Wasserstein Distance

Issued from Optimal Transport, the Wasserstein distance has gained impor...
research
03/15/2019

A nonasymptotic law of iterated logarithm for robust online estimators

In this paper, we provide tight deviation bounds for M-estimators, which...
research
11/02/2021

Outlier-Robust Optimal Transport: Duality, Structure, and Statistical Analysis

The Wasserstein distance, rooted in optimal transport (OT) theory, is a ...
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
02/20/2020

Stochastic Optimization for Regularized Wasserstein Estimators

Optimal transport is a foundational problem in optimization, that allows...
research
09/19/2019

Generalized Resilience and Robust Statistics

Robust statistics traditionally focuses on outliers, or perturbations in...
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