Markov Properties for Graphical Models with Cycles and Latent Variables
read the original abstract
We investigate probabilistic graphical models that allow for both cycles and latent variables. For this we introduce directed graphs with hyperedges (HEDGes), generalizing and combining both marginalized directed acyclic graphs (mDAGs) that can model latent (dependent) variables, and directed mixed graphs (DMGs) that can model cycles. We define and analyse several different Markov properties that relate the graphical structure of a HEDG with a probability distribution on a corresponding product space over the set of nodes, for example factorization properties, structural equations properties, ordered/local/global Markov properties, and marginal versions of these. The various Markov properties for HEDGes are in general not equivalent to each other when cycles or hyperedges are present, in contrast with the simpler case of directed acyclic graphical (DAG) models (also known as Bayesian networks). We show how the Markov properties for HEDGes - and thus the corresponding graphical Markov models - are logically related to each other.
This paper has not been read by Pith yet.
Forward citations
Cited by 4 Pith papers
-
Stable Blanket with Hidden Variables and Cycles
Graphical characterizations of Markov blankets, stable frontiers, and stable blankets are derived for causal models with hidden variables (via ADMGs and m-separation) and cycles (via DMGs, σ-separation, and strongly c...
-
Data-Driven Covariate Selection for Nonparametric and Cycle-Agnostic Causal Effect Estimation
A conditional independence-based covariate selection method for causal effects is sound and complete in cyclic models due to the invariance of conditional independence assertions under σ-acyclification.
-
Characterizing Signalling: Connections between Causal Inference and Space-time Geometry
Introduces the order-theoretic property of conicality for space-times and proves a correspondence between conical space-times and faithful information-theoretic causal models under no-superluminal-signalling constraints.
-
SCOUT: Cyclic Causal Discovery Under Soft Interventions with Unknown Targets
SCOUT recovers nonlinear cyclic causal graphs and unknown soft intervention targets from interventional data using contractive residual flows and neural spline flows to maximize log-likelihood.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.