English

Statistical inference for Bures-Wasserstein barycenters

Statistics Theory 2019-02-12 v2 Applications Statistics Theory

Abstract

In this work we introduce the concept of Bures-Wasserstein barycenter QQ_*, that is essentially a Fr\'echet mean of some distribution P\mathbb{P} supported on a subspace of positive semi-definite Hermitian operators H+(d)\mathbb{H}_{+}(d). We allow a barycenter to be restricted to some affine subspace of H+(d)\mathbb{H}_{+}(d) and provide conditions ensuring its existence and uniqueness. We also investigate convergence and concentration properties of an empirical counterpart of QQ_* in both Frobenius norm and Bures-Wasserstein distance, and explain, how obtained results are connected to optimal transportation theory and can be applied to statistical inference in quantum mechanics.

Keywords

Cite

@article{arxiv.1901.00226,
  title  = {Statistical inference for Bures-Wasserstein barycenters},
  author = {Alexey Kroshnin and Vladimir Spokoiny and Alexandra Suvorikova},
  journal= {arXiv preprint arXiv:1901.00226},
  year   = {2019}
}

Comments

37 pages, 5 figures

R2 v1 2026-06-23T07:00:59.133Z