Conditioning Methods for Exact and Approximate Inference in Causal\n Networks

2013/02/20 by Adnan Darwiche, Darwiche, Adnan
Computer Science · #Artificial Intelligence (cs.AI) #Bayesian Modeling and Causal Inference #Explainable Artificial Intelligence (XAI) #FOS: Computer and information sciences #Logic, Reasoning, and Knowledge #Machine Learning and Algorithms

paper · pdf · doi:10.48550/arxiv.1302.4939

openalex publication_date 2013/02/20 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We present two algorithms for exact and approximate inference in causal\nnetworks. The first algorithm, dynamic conditioning, is a refinement of cutset\nconditioning that has linear complexity on some networks for which cutset\nconditioning is exponential. The second algorithm, B-conditioning, is an\nalgorithm for approximate inference that allows one to trade-off the quality of\napproximations with the computation time. We also present some experimental\nresults illustrating the properties of the proposed algorithms.\n

Citations

• Fast Belief Update Using Order-of-Magnitude Probabilities

Related

• Causal Inference Using Tractable Circuits
• Inference of Causal Networks using a Topological Threshold
• A General Framework on Conditions for Constraint-based Causal Learning
• Too Fast Causal Inference under Causal Insufficiency
• Restricted Causal Inference Algorithm