ExMAG: Learning of Maximally Ancestral Graphs

Petr Ryšavý, Pavel Rytíř, Xiaoyu He, Georgios Korpas, Jakub Marecek

Keywords: causal models; maximally ancestral graphs

TL;DR: A novel score-based learning algorithm for learning maximally ancestral graphs outperforms the state of the art on modest instances (up to 25 vertices).

Abstract:

In mixed graphs, there are both directed and undirected edges. An extension of acyclicity to this mixed-graph setting is known as maximally ancestral graphs. This extension is of considerable interest in causal learning in the presence of confounders. There, directed edges represent a clear direction of causality, while undirected edges represent confounding.

We propose a score-based branch-and-cut algorithm for learning maximally ancestral graphs. The algorithm produces more accurate results than state-of-the-art methods, while being faster to run on small and medium-sized synthetic instances.

Primary Area: causal reasoning

Submission Number: 3084