Strong Completeness and Faithfulness in Bayesian Networks

Abstract

A completeness result for d-separation applied to discrete Bayesian networks is presented and it is shown that in a strong measure-theoretic sense almost all discrete distributions for a given network structure are faithful; i.e. the independence facts true of the distribution are all and only those entailed by the network structure.

Appears in Proceedings of the Eleventh Conference on Uncertainty in Artificial Intelligence (UAI1995)

Cited by in corpus (40)

• Estimating high-dimensional directed acyclic graphs with the PC-algorithm
• Quantum causal modelling
• Causal Inference in the Presence of Latent Variables and Selection Bias
• Causal interpretation rules for encoding and decoding models in neuroimaging
• Foundations of Structural Causal Models with Cycles and Latent Variables
• Strong Faithfulness and Uniform Consistency in Causal Inference
• Visual Causal Feature Learning
• Quantifier Elimination for Statistical Problems
• Markov equivalence of marginalized local independence graphs
• Scientific Inference With Interpretable Machine Learning: Analyzing Models to Learn About Real-World Phenomena
• Learning Causal Graphs with Small Interventions
• Causal Discovery from Heterogeneous/Nonstationary Data with Independent Changes
• Understanding Agent Incentives using Causal Influence Diagrams. Part I: Single Action Settings
• Causal Inference through a Witness Protection Program
• Causal inference using the algorithmic Markov condition
• On causally asymmetric versions of Occam's Razor and their relation to thermodynamics
• A Separation Theorem for Chain Event Graphs
• Beware of the Simulated DAG! Causal Discovery Benchmarks May Be Easy To Game
• A review of Gaussian Markov models for conditional independence
• Causal Conclusions that Flip Repeatedly and Their Justification
• Constraint-Based Causal Discovery using Partial Ancestral Graphs in the presence of Cycles
• Quantum Causal Structure and Quantum Thermodynamics
• Estimating Causal Direction and Confounding of Two Discrete Variables
• Faithfulness of Probability Distributions and Graphs
• On perfectness in Gaussian graphical models
• MERLiN: Mixture Effect Recovery in Linear Networks
• A Weaker Faithfulness Assumption based on Triple Interactions
• On Learning Causal Structures from Non-Experimental Data without Any Faithfulness Assumption
• Multi-Level Cause-Effect Systems
• Practically Perfect
• Using the structure of d-connecting paths as a qualitative measure of the strength of dependence
• ML4C: Seeing Causality Through Latent Vicinity
• A Topological Perspective on Causal Inference
• Obtaining Causal Information by Merging Datasets with MAXENT
• PenPC: A Two-step Approach to Estimate the Skeletons of High Dimensional Directed Acyclic Graphs
• Bayesian estimation of possible causal direction in the presence of latent confounders using a linear non-Gaussian acyclic structural equation model with individual-specific effects
• Identifying the Relevant Nodes Without Learning the Model
• Faithfulness and learning hypergraphs from discrete distributions
• Causal Discovery in Linear Structural Causal Models with Deterministic Relations
• Reading Dependencies from Polytree-Like Bayesian Networks