Partial correlation hypersurfaces in Gaussian graphical models

Jan Draisma (Corresponding author)

Research output: Contribution to journalArticleAcademicpeer-review

Abstract

We derive a combinatorial sufficient condition for a partial correlation hypersurface in the parameter space of a directed Gaussian graphical model to be nonsingular, and speculate on whether this condition can be used in algorithms for learning the graph. Since the condition is fulfilled in the case of a complete DAG on any number of vertices, the result implies an affirmative answer to a question raised by Lin–Uhler–Sturmfels–Bühlmann.
Original languageEnglish
Pages (from-to)439-446
Number of pages8
JournalAlgebraic Combinatorics
Volume2
Issue number3
DOIs
Publication statusPublished - 6 Jun 2019

Keywords

  • Gaussian graphical models
  • Partial correlation
  • Trek separation

Fingerprint

Dive into the research topics of 'Partial correlation hypersurfaces in Gaussian graphical models'. Together they form a unique fingerprint.

Cite this