Causal Markov condition for submodular information measures

Abstract

The causal Markov condition (CMC) is a postulate that links observations to causality. It describes the conditional independences among the observations that are entailed by a causal hypothesis in terms of a directed acyclic graph. In the conventional setting, the observations are random variables and the independence is a statistical one, i.e., the information content of observations is measured in terms of Shannon entropy. We formulate a generalized CMC for any kind of observations on which independence is defined via an arbitrary submodular information measure. Recently, this has been discussed for observations in terms of binary strings where information is understood in the sense of Kolmogorov complexity. Our approach enables us to find computable alternatives to Kolmogorov complexity, e.g., the length of a text after applying existing data compression schemes. We show that our CMC is justified if one restricts the attention to a class of causal mechanisms that is adapted to the respective information measure. Our justification is similar to deriving the statistical CMC from functional models of causality, where every variable is a deterministic function of its observed causes and an unobserved noise term. Our experiments on real data demonstrate the performance of compression based causal inference.

21 pages, 4 figures

References in corpus (1)

• Causal inference using the algorithmic Markov condition

Cited by in corpus (9)

• Causality for Machine Learning
• Inferring latent structures via information inequalities
• Submodular Combinatorial Information Measures with Applications in Machine Learning
• An Information-Theoretic Formalism for Multiscale Structure in Complex Systems
• SADA: A General Framework to Support Robust Causation Discovery with Theoretical Guarantee
• Switching Regression Models and Causal Inference in the Presence of Discrete Latent Variables
• Black Box Submodular Maximization: Discrete and Continuous Settings
• Independent mechanism analysis, a new concept?
• Scalable Projection-Free Optimization