Stone's theorem for distributional regression in Wasserstein distance - Archive ouverte HAL Access content directly
Preprints, Working Papers, ... Year :

Stone's theorem for distributional regression in Wasserstein distance

Abstract

We extend the celebrated Stone's theorem to the framework of distributional regression. More precisely, we prove that weighted empirical distribution with local probability weights satisfying the conditions of Stone's theorem provide universally consistent estimates of the conditional distributions, where the error is measured by the Wasserstein distance of order p ≥ 1. Furthermore, for p = 1, we determine the minimax rates of convergence on specific classes of distributions. We finally provide some applications of these results, including the estimation of conditional tail expectation or probability weighted moment.
Fichier principal
Vignette du fichier
main.pdf (285.9 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03966752 , version 1 (31-01-2023)

Licence

Attribution

Identifiers

Cite

Clément Dombry, Thibault Modeste, Romain Pic. Stone's theorem for distributional regression in Wasserstein distance. 2023. ⟨hal-03966752⟩
22 View
10 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More