On the Interventional Kullback-Leibler Divergence
Preprint
Abstract
Modern machine learning approaches excel in static settings where a large amount of i.i.d. training data are available for a given task. In a dynamic environment, though, an intelligent agent needs to be able to transfer knowledge and re-use learned components across domains. It has been argued that this may be possible through causal models, aiming to mirror the modularity of the real world in terms of independent causal mechanisms. However, the true causal structure underlying a given set of data is generally not identifiable, so it is desirable to have means to quantify differences between models (e.g., between the ground truth and an estimate), on both the observational and interventional level. In the present work, we introduce the Interventional Kullback-Leibler (IKL) divergence to quantify both structural and distributional differences between models based on a finite set of multi-environment distributions generated by interventions from the ground truth. Since we generally cannot quantify all differences between causal models for every finite set of interventional distributions, we propose a sufficient condition on the intervention targets to identify subsets of observed variables on which the models provably agree or disagree.Keywords
All Related Versions
This publication has 8 references indexed in Scilit:
- A Ladder of Causal Distances2021
- Structural Intervention Distance for Evaluating Causal GraphsNeural Computation, 2015
- Jointly Interventional and Observational Data: Estimation of Interventional Markov Equivalence Classes of Directed Acyclic GraphsJournal of the Royal Statistical Society Series B: Statistical Methodology, 2014
- Information-geometric approach to inferring causal directionsArtificial Intelligence, 2012
- The max-min hill-climbing Bayesian network structure learning algorithmMachine Learning, 2006
- Searching for Bayesian Network Structures in the Space of Restricted Acyclic Partially Directed GraphsJournal of Artificial Intelligence Research, 2003
- Causality: Models, Reasoning and InferencePhilosophical Review, 2001
- Causation, Prediction, and Search1993