# Hellinger-Kantorovich barycenter between Dirac measures

arXiv: https://arxiv.org/abs/2206.11211 · HTML: https://mlsanity.com/paper/2206.11211/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Jun 2022.

## Built on by (most cited first, 2 of 2)

- [Robust Barycenter Estimation using Semi-Unbalanced Neural Optimal Transport](https://mlsanity.com/paper/2410.03974/) (2024)
- [Neighbor Embeddings Using Unbalanced Optimal Transport Metrics](https://mlsanity.com/paper/2509.19226/) (2025)

## Abstract (arXiv)

The Hellinger-Kantorovich (HK) distance is an unbalanced extension of the Wasserstein-2 distance. It was shown recently that the HK barycenter exhibits a much more complex behaviour than the Wasserstein barycenter. Motivated by this observation we study the HK barycenter in more detail for the case where the input measures are an uncountable collection of Dirac measures, in particular the dependency on the length scale parameter of HK, the question whether the HK barycenter is discrete or continuous and the relation between the expected and the empirical barycenter. The analytical results are complemented with numerical experiments that demonstrate that the HK barycenter can provide a coarse-to-fine representation of an input pointcloud or measure.