Minimal Gelbrich Distance to Uncorrelation - Archive ouverte HAL
Article Dans Une Revue IEEE Control Systems Letters Année : 2023

Minimal Gelbrich Distance to Uncorrelation

Résumé

This letter reports new properties of the Wasserstein/Gelbrich distance and associated ambiguity sets to analyze the correlation between two scalar random variables. A simple closed expression is derived for the Gelbrich distance between two bidimensional random distributions. Moreover, the minimum disturbance in the Gelbrich metric required to reach uncorrelation between two random variables is obtained. This allows us to determine the robustness of the Pearson coefficient within an ambiguity set. A numerical example showcases the potential use of the obtained results in the field of variable selection.
Fichier principal
Vignette du fichier
DTIS2023-220-2023_LCSS-Acceptée.pdf (409.48 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04379498 , version 1 (31-05-2024)
hal-04379498 , version 2 (29-07-2024)

Identifiants

Citer

Matthieu Borelle, Teodoro Alamo, Cristina Stoica Maniu, Sylvain Bertrand, Eduardo Camacho. Minimal Gelbrich Distance to Uncorrelation. IEEE Control Systems Letters, 2023, 8, pp.61-66. ⟨10.1109/LCSYS.2023.3343990⟩. ⟨hal-04379498v1⟩
134 Consultations
41 Téléchargements

Altmetric

Partager

More