Minimax estimation of smooth densities in Wasserstein distance

DOI10.1214/21-AOS2161arXiv1902.01778MaRDI QIDQ6313635FDOQ6313635

Jonathan Niles-Weed, Quentin Berthet

Publication date: 5 February 2019

Abstract: We study nonparametric density estimation problems where error is measured in the Wasserstein distance, a metric on probability distributions popular in many areas of statistics and machine learning. We give the first minimax-optimal rates for this problem for general Wasserstein distances, and show that, unlike classical nonparametric density estimation, these rates depend on whether the densities in question are bounded below. Motivated by variational problems involving the Wasserstein distance, we also show how to construct discretely supported measures, suitable for computational purposes, which achieve the minimax rates. Our main technical tool is an inequality giving a nearly tight dual characterization of the Wasserstein distances in terms of Besov norms.

Mathematics Subject Classification ID

Convergence of probability measures (60B10) Density estimation (62G07) Nontrigonometric harmonic analysis involving wavelets and other special systems (42C40) Optimal transportation (49Q22) Estimation in multivariate analysis (62H12)

This page was built for publication: Minimax estimation of smooth densities in Wasserstein distance

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6313635)