Simulation of the matrix Bingham-von Mises-Fisher distribution, with applications to multivariate and relational data

Simple item page
dc.creatorHoff, Peter
dc.date2007-12-27
dc.date.accessioned2026-07-07T08:51:22Z
dc.date.available2026-07-07T08:51:22Z
dc.descriptionOrthonormal matrices play an important role in reduced-rank matrix approximations and the analysis of matrix-valued data. A matrix Bingham-von Mises-Fisher distribution is a probability distribution on the set of orthonormal matrices that includes linear and quadratic terms, and arises as a posterior distribution in latent factor models for multivariate and relational data. This article describes rejection and Gibbs sampling algorithms for sampling from this family of distributions, and illustrates their use in the analysis of a protein-protein interaction network.
dc.description17 pages, 3 figures, 1 table
dc.identifierhttps://arxiv.org/abs/0712.4166
dc.identifierhttp://arxiv.org/abs/0712.4166
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/144912
dc.subjectComputation
dc.subjectMethodology
dc.titleSimulation of the matrix Bingham-von Mises-Fisher distribution, with applications to multivariate and relational data
dc.typetext

Files

Collections

arXiv