A Geometric Condition for Uniqueness of Fr\'echet Means of Persistence Diagrams

arXiv2207.03943MaRDI QIDQ6404413FDOQ6404413

Publication date: 8 July 2022

Abstract: The Fr'echet mean is an important statistical summary and measure of centrality of data; it has been defined and studied for persistent homology captured by persistence diagrams. However, the complicated geometry of the space of persistence diagrams implies that the Fr'echet mean for a given set of persistence diagrams is not necessarily unique, which prohibits theoretical guarantees for empirical means with respect to population means. In this paper, we derive a variance expression for a set of persistence diagrams exhibiting a multi-matching between the persistence points known as a grouping. Moreover, we propose a condition for groupings, which we refer to as flatness: sets of persistence diagrams that exhibit flat groupings give rise to unique Fr'echet means. We derive a finite sample convergence result for general groupings, which results in convergence for Fr'echet means if the groupings are flat. Finally, we interpret flat groupings in a recently-proposed general framework of Fr'echet means in Alexandrov geometry. Together with recent results from Alexandrov geometry, this allows for the first derivation of a finite sample convergence rate for sets of persistence diagrams and lays the ground for viability of the Fr'echet mean as a practical statistical summary of persistent homology.

This page was built for publication: A Geometric Condition for Uniqueness of Fr\'echet Means of Persistence Diagrams

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6404413)