Universal Approximation on the Hypersphere

DOI10.1080/03610926.2021.1904988MaRDI QIDQ6338647arXivFDO

Authors Tin Lok James Ng, Kwok-Kun Kwong

Publication date 14 April 2020

Published in arXiv

Full work available at URL https://doi.org/10.1080/03610926.2021.1904988

Mathematics Subject Classification ID

Statistics (62-XX)

arXiv classification

math.STstat.MEstat.TH

Abstract: It is well known that any continuous probability density function on $mathbb{R}^m$ can be approximated arbitrarily well by a finite mixture of normal distributions, provided that the number of mixture components is sufficiently large. The von-Mises-Fisher distribution, defined on the unit hypersphere $S^m$ in $mathbb{R}^{m+1}$, has properties that are analogous to those of the multivariate normal on $mathbb{R}^{m+1}$. We prove that any continuous probability density function on $S^m$ can be approximated to arbitrary degrees of accuracy by a finite mixture of von-Mises-Fisher distributions.

This page was built for publication: Universal Approximation on the Hypersphere

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6338647)