On the attainment of the Wasserstein--Cramer--Rao lower bound

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Nishimori, Hayato, Matsuda, Takeru
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908499843219456
author Nishimori, Hayato
Matsuda, Takeru
author_facet Nishimori, Hayato
Matsuda, Takeru
contents Recently, a Wasserstein analogue of the Cramer--Rao inequality has been developed using the Wasserstein information matrix (Otto metric). This inequality provides a lower bound on the Wasserstein variance of an estimator, which quantifies its robustness against additive noise. In this study, we investigate conditions for an estimator to attain the Wasserstein--Cramer--Rao lower bound (asymptotically), which we call the (asymptotic) Wasserstein efficiency. We show a condition under which Wasserstein efficient estimators exist for one-parameter statistical models. This condition corresponds to a recently proposed Wasserstein analogue of one-parameter exponential families (e-geodesics). We also show that the Wasserstein estimator, a Wasserstein analogue of the maximum likelihood estimator based on the Wasserstein score function, is asymptotically Wasserstein efficient in location-scale families.
format Preprint
id arxiv_https___arxiv_org_abs_2506_12732
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle On the attainment of the Wasserstein--Cramer--Rao lower bound
Nishimori, Hayato
Matsuda, Takeru
Statistics Theory
Machine Learning
Recently, a Wasserstein analogue of the Cramer--Rao inequality has been developed using the Wasserstein information matrix (Otto metric). This inequality provides a lower bound on the Wasserstein variance of an estimator, which quantifies its robustness against additive noise. In this study, we investigate conditions for an estimator to attain the Wasserstein--Cramer--Rao lower bound (asymptotically), which we call the (asymptotic) Wasserstein efficiency. We show a condition under which Wasserstein efficient estimators exist for one-parameter statistical models. This condition corresponds to a recently proposed Wasserstein analogue of one-parameter exponential families (e-geodesics). We also show that the Wasserstein estimator, a Wasserstein analogue of the maximum likelihood estimator based on the Wasserstein score function, is asymptotically Wasserstein efficient in location-scale families.
title On the attainment of the Wasserstein--Cramer--Rao lower bound
topic Statistics Theory
Machine Learning
url https://arxiv.org/abs/2506.12732