Differentiable Multi-Target Causal Bayesian Experimental Design

Panagiotis Tigas, Yashas Annadani, Desi R. Ivanova, Andrew Jesson, Yarin Gal, Adam Foster, Stefan Bauer

Keywords: Causality, Bayesian Optimal Experimental Design, Active Learning

TL;DR: We introduce differentiable approximations of Expected Information Gain for acquiring multi-target-state interventions in a batch setting to learn causal models.

Abstract: We introduce a gradient-based approach for the problem of Bayesian optimal experimental design to learn causal models in a batch setting --- a critical component for causal discovery from finite data where interventions can be costly or risky. Existing methods rely on greedy approximations to construct a batch of experiments while using black-box methods to optimize over a single target-state pair to intervene with. In this work, we completely dispose of the black-box optimization techniques and greedy heuristics and instead propose a conceptually simple end-to-end gradient-based optimization procedure to acquire a set of optimal intervention target-state pairs. Such a procedure enables parameterization of the design space to efficiently optimize over a batch of multi-target-state interventions, a setting which has hitherto not been explored due to its complexity. We demonstrate that our proposed method outperforms baselines and existing acquisition strategies in both single-target and multi-target settings across a number of synthetic datasets.

Community Implementations: [ 2 code implementations](https://www.catalyzex.com/paper/arxiv:2302.10607/code)