Smooth p-Wasserstein Distance: Structure, Empirical Approximation, and Statistical Applications

MaRDI QIDQ6358035arXivFDO

Authors Sloan Nietert, Ziv Goldfeld, Kengo Kato

Publication date 11 January 2021

Published in arXiv

arXiv classification

math.STstat.MLstat.TH

Abstract: Discrepancy measures between probability distributions, often termed statistical distances, are ubiquitous in probability theory, statistics and machine learning. To combat the curse of dimensionality when estimating these distances from data, recent work has proposed smoothing out local irregularities in the measured distributions via convolution with a Gaussian kernel. Motivated by the scalability of this framework to high dimensions, we investigate the structural and statistical behavior of the Gaussian-smoothed $p$-Wasserstein distance $mathsf{W}_p^{(sigma)}$, for arbitrary $pgeq1$. After establishing basic metric and topological properties of $mathsf{W}_p^{(sigma)}$, we explore the asymptotic statistical behavior of $mathsf{W}_p^{(sigma)}(hat{mu}_n,mu)$, where $hat{mu}_n$ is the empirical distribution of $n$ independent observations from $mu$. We prove that $mathsf{W}_p^{(sigma)}$ enjoys a parametric empirical convergence rate of $n^{-1/2}$, which contrasts the $n^{-1/d}$ rate for unsmoothed $mathsf{W}_p$ when $dgeq3$. Our proof relies on controlling $mathsf{W}_p^{(sigma)}$ by a $p$th-order smooth Sobolev distance $mathsf{d}_p^{(sigma)}$ and deriving the limit distribution of $sqrtn,mathsf{d}_p^{(sigma)}(hat{mu}_n,mu)$, for all dimensions $d$. As applications, we provide asymptotic guarantees for two-sample testing and minimum distance estimation using $mathsf{W}_p^{(sigma)}$, with experiments for $p=2$ using a maximum mean discrepancy formulation of $mathsf{d}_2^{(sigma)}$.

Cited in

(1)

• Optimal Transport Bounds for Latent Density Smoothing on MTW($K>0$) Manifolds

This page was built for publication: Smooth $p$-Wasserstein Distance: Structure, Empirical Approximation, and Statistical Applications

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6358035)