On generating random Gaussian graphical models

Research output: Contribution to journalJournal articlepeer-review

  • Irene Córdoba
  • Gherardo Varando
  • Concha Bielza
  • Pedro Larrañaga

Structure learning methods for covariance and concentration graphs are often validated on synthetic models, usually obtained by randomly generating: (i) an undirected graph, and (ii) a compatible symmetric positive definite (SPD) matrix. In order to ensure positive definiteness in (ii), a dominant diagonal is usually imposed. In this work we investigate different methods to generate random symmetric positive definite matrices with undirected graphical constraints. We show that if the graph is chordal it is possible to sample uniformly from the set of correlation matrices compatible with the graph, while for general undirected graphs we rely on a partial orthogonalization method.

Original languageEnglish
JournalInternational Journal of Approximate Reasoning
Volume125
Pages (from-to)240-250
Number of pages11
ISSN0888-613X
DOIs
Publication statusPublished - 2020

    Research areas

  • Algorithm validation, Concentration graph, Covariance graph, Positive definite matrix simulation, Undirected graphical model

Links

ID: 248192670