Bi-invariant Dissimilarity Measures for Sample Distributions in Lie Groups

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Hanik, Martin, Hege, Hans-Christian, von Tycowicz, Christoph
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866910337427570688
author Hanik, Martin
Hege, Hans-Christian
von Tycowicz, Christoph
author_facet Hanik, Martin
Hege, Hans-Christian
von Tycowicz, Christoph
contents Data sets sampled in Lie groups are widespread, and as with multivariate data, it is important for many applications to assess the differences between the sets in terms of their distributions. Indices for this task are usually derived by considering the Lie group as a Riemannian manifold. Then, however, compatibility with the group operation is guaranteed only if a bi-invariant metric exists, which is not the case for most non-compact and non-commutative groups. We show here that if one considers an affine connection structure instead, one obtains bi-invariant generalizations of well-known dissimilarity measures: a Hotelling $T^2$ statistic, Bhattacharyya distance and Hellinger distance. Each of the dissimilarity measures matches its multivariate counterpart for Euclidean data and is translation-invariant, so that biases, e.g., through an arbitrary choice of reference, are avoided. We further derive non-parametric two-sample tests that are bi-invariant and consistent. We demonstrate the potential of these dissimilarity measures by performing group tests on data of knee configurations and epidemiological shape data. Significant differences are revealed in both cases.
format Preprint
id arxiv_https___arxiv_org_abs_2402_12901
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Bi-invariant Dissimilarity Measures for Sample Distributions in Lie Groups
Hanik, Martin
Hege, Hans-Christian
von Tycowicz, Christoph
Methodology
Statistics Theory
62R30 22E70 62R30, 22E70, 53Z50
Data sets sampled in Lie groups are widespread, and as with multivariate data, it is important for many applications to assess the differences between the sets in terms of their distributions. Indices for this task are usually derived by considering the Lie group as a Riemannian manifold. Then, however, compatibility with the group operation is guaranteed only if a bi-invariant metric exists, which is not the case for most non-compact and non-commutative groups. We show here that if one considers an affine connection structure instead, one obtains bi-invariant generalizations of well-known dissimilarity measures: a Hotelling $T^2$ statistic, Bhattacharyya distance and Hellinger distance. Each of the dissimilarity measures matches its multivariate counterpart for Euclidean data and is translation-invariant, so that biases, e.g., through an arbitrary choice of reference, are avoided. We further derive non-parametric two-sample tests that are bi-invariant and consistent. We demonstrate the potential of these dissimilarity measures by performing group tests on data of knee configurations and epidemiological shape data. Significant differences are revealed in both cases.
title Bi-invariant Dissimilarity Measures for Sample Distributions in Lie Groups
topic Methodology
Statistics Theory
62R30 22E70 62R30, 22E70, 53Z50
url https://arxiv.org/abs/2402.12901