Limit distribution theory for smooth p-Wasserstein distances

03/01/2022
by   Ziv Goldfeld, et al.
0

The Wasserstein distance is a metric on a space of probability measures that has seen a surge of applications in statistics, machine learning, and applied mathematics. However, statistical aspects of Wasserstein distances are bottlenecked by the curse of dimensionality, whereby the number of data points needed to accurately estimate them grows exponentially with dimension. Gaussian smoothing was recently introduced as a means to alleviate the curse of dimensionality, giving rise to a parametric convergence rate in any dimension, while preserving the Wasserstein metric and topological structure. To facilitate valid statistical inference, in this work, we develop a comprehensive limit distribution theory for the empirical smooth Wasserstein distance. The limit distribution results leverage the functional delta method after embedding the domain of the Wasserstein distance into a certain dual Sobolev space, characterizing its Hadamard directional derivative for the dual Sobolev norm, and establishing weak convergence of the smooth empirical process in the dual space. To estimate the distributional limits, we also establish consistency of the nonparametric bootstrap. Finally, we use the limit distribution theory to study applications to generative modeling via minimum distance estimation with the smooth Wasserstein distance, showing asymptotic normality of optimal solutions for the quadratic cost.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/11/2021

From Smooth Wasserstein Distance to Dual Sobolev Norm: Empirical Approximation and Statistical Applications

Statistical distances, i.e., discrepancy measures between probability di...
research
05/31/2023

Entropic Gromov-Wasserstein Distances: Stability, Algorithms, and Distributional Limits

The Gromov-Wasserstein (GW) distance quantifies discrepancy between metr...
research
07/28/2021

Limit Distribution Theory for the Smooth 1-Wasserstein Distance with Applications

The smooth 1-Wasserstein distance (SWD) W_1^σ was recently proposed as a...
research
06/22/2020

Gromov-Wasserstein Distance based Object Matching: Asymptotic Inference

In this paper, we aim to provide a statistical theory for object matchin...
research
01/31/2021

Measuring association with Wasserstein distances

Let π∈Π(μ,ν) be a coupling between two probability measures μ and ν on a...
research
06/14/2018

Statistical Aspects of Wasserstein Distances

Wasserstein distances are metrics on probability distributions inspired ...
research
05/09/2022

Statistical inference with regularized optimal transport

Optimal transport (OT) is a versatile framework for comparing probabilit...

Please sign up or login with your details

Forgot password? Click here to reset