Lower Bounds on the Size of Markov Equivalence Classes

Erik L Jahn, Frederick Eberhardt, Leonard Schulman

Keywords: Causal Graphs, Markov Equivalence Classes, Causal Discovery

TL;DR: We prove exponential lower bounds on the expected size of Markov equivalence classes of sparse random DAGs, uniformly random ADMGs and uniformly random DCGs.

Abstract: Causal discovery algorithms typically recover causal graphs only up to their Markov equivalence classes unless additional parametric assumptions are made. The sizes of these equivalence classes reflect the limits of what can be learned about the underlying causal graph from purely observational data. Under the assumptions of acyclicity, causal sufficiency, and a uniform model prior, Markov equivalence classes are known to be small on average. In this paper, we show that this is no longer the case when any of these assumptions is relaxed. Specifically, we prove exponentially large lower bounds for the expected size of Markov equivalence classes in three settings: sparse random directed acyclic graphs, uniformly random acyclic directed mixed graphs, and uniformly random directed cyclic graphs.

Readers: auai.org/UAI/2025/Conference, auai.org/UAI/2025/Conference/Area_Chairs, auai.org/UAI/2025/Conference/Reviewers, auai.org/UAI/2025/Conference/Submission734/Authors, auai.org/UAI/2025/Conference/Submission734/Reproducibility_Reviewers

Submission Number: 734