Probability trees and the value of a single intervention

2022/05/18 by Tue Herlau, Herlau, Tue
Computer Science · #68T37 #Bayesian Modeling and Causal Inference #FOS: Computer and information sciences #I.5.1 #Machine Learning (cs.LG) #Machine Learning and Algorithms #Methodology (stat.ME)

paper · pdf · doi:10.48550/arxiv.2205.08779

openalex publication_date 2022/05/18 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

The most fundamental problem in statistical causality is determining causal relationships from limited data. Probability trees, which combine prior causal structures with Bayesian updates, have been suggested as a possible solution. In this work, we quantify the information gain from a single intervention and show that both the anticipated information gain, prior to making an intervention, and the expected gain from an intervention have simple expressions. This results in an active-learning method that simply selects the intervention with the highest anticipated gain, which we illustrate through several examples. Our work demonstrates how probability trees, and Bayesian estimation of their parameters, offer a simple yet viable approach to fast causal induction.

Related

• Active learning of causal probability trees
• Bayesian Causal Induction
• Algorithms for Causal Reasoning in Probability Trees
• Causal Structure Learning: a Bayesian approach based on random graphs
• Learning Link-Probabilities in Causal Trees