Self-Compatibility: Evaluating Causal Discovery without Ground Truth

arXiv:2307.09552v2 Announce Type: replace
Abstract: As causal ground truth is incredibly rare, causal discovery algorithms are commonly only evaluated on simulated data. This is concerning, given that simulations reflect preconceptions about generating processes regarding noise distributions, model classes, and more. In this work, we propose a novel method for falsifying the output of a causal discovery algorithm in the absence of ground truth. Our key insight is that while statistical learning seeks stability across subsets of data points, causal learning …

abstract algorithms arxiv causal cs.lg data discovery noise novel processes simulated data simulations stat.me stat.ml truth type work