English

Fisher-Bingham-like normalizing flows on the sphere

Machine Learning 2025-10-07 v1 Instrumentation and Methods for Astrophysics Artificial Intelligence Machine Learning

Abstract

A generic D-dimensional Gaussian can be conditioned or projected onto the D-1 unit sphere, thereby leading to the well-known Fisher-Bingham (FB) or Angular Gaussian (AG) distribution families, respectively. These are some of the most fundamental distributions on the sphere, yet cannot straightforwardly be written as a normalizing flow except in two special cases: the von-Mises Fisher in D=3 and the central angular Gaussian in any D. In this paper, we describe how to generalize these special cases to a family of normalizing flows that behave similarly to the full FB or AG family in any D. We call them "zoom-linear-project" (ZLP)-Fisher flows. Unlike a normal Fisher-Bingham distribution, their composition allows to gradually add complexity as needed. Furthermore, they can naturally handle conditional density estimation with target distributions that vary by orders of magnitude in scale - a setting that is important in astronomical applications but that existing flows often struggle with. A particularly useful member of the new family is the Kent analogue that can cheaply upgrade any flow in this situation to yield better performance.

Cite

@article{arxiv.2510.04762,
  title  = {Fisher-Bingham-like normalizing flows on the sphere},
  author = {Thorsten Glüsenkamp},
  journal= {arXiv preprint arXiv:2510.04762},
  year   = {2025}
}
R2 v1 2026-07-01T06:18:59.870Z