A Geometric Condition for Uniqueness of Fréchet Means of Persistence Diagrams
share
The Fréchet 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 Fréchet mean for a given set of persistence diagrams is generally not 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 Fréchet means. Together with recent results from Alexandrov geometry, this allows for the first derivation of a finite sample convergence rate for sets of persistence diagrams that exhibit flat groupings.
READ FULL TEXT