Coloured Graphical Models and their Symmetries

2020/12/03 by Isobel Davies, Davies, Isobel, Orlando Marigliano +1 · 1 citation
Computer Science · #05C50 #62R01 #Algebraic Geometry (math.AG) #Bayesian Modeling and Causal Inference #Data Management and Algorithms #Data Visualization and Analytics #FOS: Mathematics #Statistics Theory (math.ST)

paper · pdf · doi:10.48550/arxiv.2012.01905

openalex publication_date 2020/12/03 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Coloured graphical models are Gaussian statistical models determined by an undirected coloured graph. These models can be described by linear spaces of symmetric matrices. We outline a relationship between the symmetries of the graph and the linear forms that vanish on the reciprocal variety of the model. In particular, we give four families for which such linear forms are completely described by symmetries.

Cited by

• Linear relations of colored Gaussian cycles

Related

• Symmetries in Directed Gaussian Graphical Models
• Linear relations of colored Gaussian cycles
• Parametric and nonparametric symmetries in graphical models for extremes
• Graphical Gaussian models associated to a homogeneous graph with permutation symmetries
• Symmetries of stochastic colored vertex models