Trust Your $\nabla$: Gradient-based Intervention Targeting for Causal Discovery

arXiv:2211.13715v4 Announce Type: replace-cross
Abstract: Inferring causal structure from data is a challenging task of fundamental importance in science. Observational data are often insufficient to identify a system's causal structure uniquely. While conducting interventions (i.e., experiments) can improve the identifiability, such samples are usually challenging and expensive to obtain. Hence, experimental design approaches for causal discovery aim to minimize the number of interventions by estimating the most informative intervention target. In this work, we propose a novel Gradient-based Intervention Targeting …

abstract arxiv cs.ai cs.lg data discovery experimental gradient identify importance nabla samples science stat.me stat.ml targeting trust type