Large Sample Theory for Bures-Wasserstein Barycentres

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Santoro, Leonardo V., Panaretos, Victor M.
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866929574883885056
author Santoro, Leonardo V.
Panaretos, Victor M.
author_facet Santoro, Leonardo V.
Panaretos, Victor M.
contents We establish a strong law of large numbers and a central limit theorem in the Bures-Wasserstein space of covariance operators -- or equivalently centred Gaussian measures -- over a general separable Hilbert space. Specifically, we show that empirical barycentre sequences indexed by sample size are almost certainly relatively compact, with accumulation points comprising population barycentres. We give a sufficient regularity condition for the limit to be unique. When the limit is unique, we also establish a central limit theorem under a refined pair of moment and regularity conditions. Finally, we prove strong operator convergence of the empirical optimal transport maps to their population counterparts. Though our results naturally extend finite-dimensional counterparts, including associated regularity conditions, our techniques are distinctly different owing to the functional nature of the problem in the general setting. A key element is the characterisation of compact sets in the Bures-Wasserstein topology that reflects an ordered Heine-Borel property of the Bures-Wasserstein space.
format Preprint
id arxiv_https___arxiv_org_abs_2305_15592
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Large Sample Theory for Bures-Wasserstein Barycentres
Santoro, Leonardo V.
Panaretos, Victor M.
Probability
Statistics Theory
60B12, 60G57, 60H25, 62R20, 62R30
We establish a strong law of large numbers and a central limit theorem in the Bures-Wasserstein space of covariance operators -- or equivalently centred Gaussian measures -- over a general separable Hilbert space. Specifically, we show that empirical barycentre sequences indexed by sample size are almost certainly relatively compact, with accumulation points comprising population barycentres. We give a sufficient regularity condition for the limit to be unique. When the limit is unique, we also establish a central limit theorem under a refined pair of moment and regularity conditions. Finally, we prove strong operator convergence of the empirical optimal transport maps to their population counterparts. Though our results naturally extend finite-dimensional counterparts, including associated regularity conditions, our techniques are distinctly different owing to the functional nature of the problem in the general setting. A key element is the characterisation of compact sets in the Bures-Wasserstein topology that reflects an ordered Heine-Borel property of the Bures-Wasserstein space.
title Large Sample Theory for Bures-Wasserstein Barycentres
topic Probability
Statistics Theory
60B12, 60G57, 60H25, 62R20, 62R30
url https://arxiv.org/abs/2305.15592