Symmetrically Colored Gaussian Graphical Models with Toric Vanishing Ideals

DOI10.1137/21M1466943OpenAlexW4361289511MaRDI QIDQ6043374FDOQ6043374

Authors Jane Ivy Coons, Aida Maraj, Pratik Misra, Miruna-Ştefana Sorea

Publication date 5 May 2023

Published in SIAM Journal on Applied Algebra and Geometry (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2111.14817

zbMATH Keywords

toric varietiesJordan algebrasMarkov baseslinear concentration modelscolored Gaussian graphical modelsRCOP models

Mathematics Subject Classification ID

Probabilistic graphical models (62H22) Algebraic statistics (62R01) Coloring of graphs and hypergraphs (05C15) Applications of commutative algebra (e.g., to statistics, control theory, optimization, etc.) (13P25)

Abstract: A colored Gaussian graphical model is a linear concentration model in which equalities among the concentrations are specified by a coloring of an underlying graph. The model is called RCOP if this coloring is given by the edge and vertex orbits of a subgroup of the automorphism group of the graph. We show that RCOP Gaussian graphical models on block graphs are toric in the space of covariance matrices and we describe Markov bases for them. To this end, we learn more about the combinatorial structure of these models and their connection with Jordan algebras.

Recommendations

• Gaussian graphical models with toric vanishing ideals
• Coloured graphical models and their symmetries
• Directed Gaussian graphical models with toric vanishing ideals
• Graphical Gaussian Models With Edge and Vertex Symmetries
• Lattices of graphical Gaussian models with symmetries
• On the toric algebra of graphical models
• Estimation of means in graphical Gaussian models with symmetries
• Symmetries in directed Gaussian graphical models
• Graphical models for sparse data: graphical Gaussian models with vertex and edge symmetries
• Matrix Schubert varieties and Gaussian conditional independence models

Cites work

• Algebraic algorithms for sampling from conditional distributions
• Binomial ideals
• Brownian motion tree models are toric
• Covariance hypothesis which are linear in both the covariance and the inverse covariance
• Estimation of means in graphical Gaussian models with symmetries
• Gaussian graphical models with toric vanishing ideals
• Graphical Gaussian Models With Edge and Vertex Symmetries
• Jordan algebras of symmetric matrices
• Model selection for factorial Gaussian graphical models with an application to dynamic regulatory networks
• Multivariate Gaussians, semidefinite matrix completion, and convex algebraic geometry
• Necessary and sufficient conditions for explicit solutions in the multivariate normal estimation problem for patterned means and covariances
• On an algebraic generalization of the quantum mechanical formalism
• Reciprocal maximum likelihood degrees of Brownian motion tree models

This page was built for publication: Symmetrically Colored Gaussian Graphical Models with Toric Vanishing Ideals

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6043374)