Barycenters for the Hellinger--Kantorovich distance over ${\mathbb{R}}^d$

Abstract

We study the barycenter of the Hellinger--Kantorovich metric over non-negative measures on compact, convex subsets of ${\mathbb{R}}^d$. The article establishes existence, uniqueness (under suitable assumptions) and equivalence between a coupled-two-marginal and a multi-marginal formulation. We analyze the HK barycenter between Dirac measures in detail, and find that it differs substantially from the Wasserstein barycenter by exhibiting a local `clustering' behaviour, depending on the length scale of the input measures. In applications it makes sense to simultaneously consider all choices of this scale, leading to a 1-parameter family of barycenters. We demonstrate the usefulness of this family by analyzing point clouds sampled from a mixture of Gaussians and inferring the number and location of the underlying Gaussians.

Minor changes to keep consistent with journal version