Bayesian Optimal Experimental Design for Inferring Causal Structure

TL;DR

This paper introduces a Bayesian approach for optimal experimental design to efficiently infer causal structures by selecting interventions that rapidly reduce uncertainty, demonstrated through simulations and real data applications.

Contribution

The paper presents a novel Bayesian method for sequential intervention selection that minimizes posterior entropy without intensive computations, specifically applied to causal network inference.

Findings

Method outperforms existing approaches in simulations

Efficient intervention selection reduces experimental costs

Successfully applied to protein-signaling network data

Abstract

Inferring the causal structure of a system typically requires interventional data, rather than just observational data. Since interventional experiments can be costly, it is preferable to select interventions that yield the maximum amount of information about a system. We propose a novel Bayesian method for optimal experimental design by sequentially selecting interventions that minimize the expected posterior entropy as rapidly as possible. A key feature is that the method can be implemented by computing simple summaries of the current posterior, avoiding the computationally burdensome task of repeatedly performing posterior inference on hypothetical future datasets drawn from the posterior predictive. After deriving the method in a general setting, we apply it to the problem of inferring causal networks. We present a series of simulation studies in which we find that the proposed method performs favorably compared to existing alternative methods. Finally, we apply the method to real and simulated data from a protein-signaling network.