A genericity property of Fr\'echet sample means on Riemannian manifolds
Abstract
Let (M,g) be a Riemannian manifold. If μ is a probability measure on M given by a continuous density function, one would expect the Fr\'echet means of data-samples Q=(q1,q2,…, qN)∈ MN, with respect to μ, to behave ``generically''; e.g. the probability that the Fr\'echet mean set FM(Q) has any elements that lie in a given, positive-codimension submanifold, should be zero for any N≥ 1. Even this simplest instance of genericity does not seem to have been proven in the literature, except in special cases. The main result of this paper is a general, and stronger, genericity property: given i.i.d. absolutely continuous M-valued random variables X1,…, XN, and a subset A⊂ M of volume-measure zero, Pr\FM(\X1,…,XN\)⊂ M A\=1. We also establish a companion theorem for equivariant Fr\'echet means, defined when (M,g) arises as the quotient of a Riemannian manifold (M,g) by a free, isometric action of a finite group. The equivariant Fr\'echet means lie in M, but, as we show, project down to the ordinary Fr\'echet sample means, and enjoy a similar genericity property. Both these theorems are proven as consequences of a purely geometric (and quite general) result that constitutes the core mathematics in this paper: If A⊂ M has volume zero in M , then the set \Q∈ MN : FM(Q) A≠\ has volume zero in MN. We conclude the paper with an application to partial scaling-rotation means, a type of mean for symmetric positive-definite matrices.
Turn this paper into a lesson
ArcXiv compiles a structured reading guide from this paper's metadata: plain-English importance, contributions, prerequisite concepts, which sections to read first, flashcards, and a quiz. Grounded in the abstract, never invented.