On Projection Robust Optimal Transport: Sample Complexity and Model Misspecification

06/22/2020
by   Tianyi Lin, et al.
0

Optimal transport (OT) distances are increasingly used as loss functions for statistical inference, notably in the learning of generative models or supervised learning. Yet, the behavior of minimum Wasserstein estimators is poorly understood, notably in high-dimensional regimes or under model misspecification. In this work we adopt the viewpoint of projection robust (PR) OT, which seeks to maximize the OT cost between two measures by choosing a k-dimensional subspace onto which they can be projected. Our first contribution is to establish several fundamental statistical properties of PR Wasserstein distances, complementing and improving previous literature that has been restricted to one-dimensional and well-specified cases. Next, we propose the integral PR Wasserstein (IPRW) distance as an alternative to the PRW distance, by averaging rather than optimizing on subspaces. Our complexity bounds can help explain why both PRW and IPRW distances outperform Wasserstein distances empirically in high-dimensional inference tasks. Finally, we consider parametric inference using the PRW distance. We provide an asymptotic guarantee of two types of minimum PRW estimators and formulate a central limit theorem for max-sliced Wasserstein estimator under model misspecification. To enable our analysis on PRW with projection dimension larger than one, we devise a novel combination of variational analysis and statistical theory.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/25/2019

Subspace Robust Wasserstein distances

Making sense of Wasserstein distances between discrete measures in high-...
research
08/04/2021

Statistical Analysis of Wasserstein Distributionally Robust Estimators

We consider statistical methods which invoke a min-max distributionally ...
research
07/26/2021

Plugin Estimation of Smooth Optimal Transport Maps

We analyze a number of natural estimators for the optimal transport map ...
research
05/18/2018

Computing Kantorovich-Wasserstein Distances on d-dimensional histograms using (d+1)-partite graphs

This paper presents a novel method to compute the exact Kantorovich-Wass...
research
04/11/2019

Max-Sliced Wasserstein Distance and its use for GANs

Generative adversarial nets (GANs) and variational auto-encoders have si...
research
08/29/2016

Wasserstein Discriminant Analysis

Wasserstein Discriminant Analysis (WDA) is a new supervised method that ...
research
01/02/2019

Statistical inference for Bures-Wasserstein barycenters

In this work we introduce the concept of Bures-Wasserstein barycenter Q_...

Please sign up or login with your details

Forgot password? Click here to reset