Theoretical Guarantees for Causal Discovery on Large Random Graphs

TL;DR

This paper provides the first dimension-adaptive theoretical guarantees for causal discovery accuracy in large random graphs, showing that error rates concentrate and diminish with increasing network size, even under complex topologies.

Contribution

It introduces novel finite-dimensional, faithfulness-robust bounds for causal structure learning on large, random, and scale-free graphs, challenging prior assumptions about high-dimensional difficulties.

Findings

FNR concentrates around its mean at rate O(log d / sqrt d) for Erdős–Rényi graphs.

For Barabási–Albert graphs with degree exponent > 3, deviation width vanishes as dimension increases.

Simulation results confirm theoretical concentration and error reduction in large-scale settings.

Abstract

We investigate theoretical guarantees for the false-negative rate (FNR) -- the fraction of true causal edges whose orientation is not recovered, under single-variable random interventions and an $\epsilon$-interventional faithfulness assumption that accommodates latent confounding. For sparse Erd\H{o}s--R\'enyi directed acyclic graphs, where the edge probability scales as $p_e = \Theta(1/d)$, we show that the FNR concentrates around its mean at rate $O(\frac{\log d}{\sqrt d})$, implying that large deviations above the expected error become exponentially unlikely as dimensionality increases. This concentration ensures that derived upper bounds hold with high probability in large-scale settings. Extending the analysis to generalized Barab\'asi--Albert graphs reveals an even stronger phenomenon: when the degree exponent satisfies $\gamma > 3$, the deviation width scales as $O(d^{\beta - \frac{1}{2}})$ with $\beta = 1/(\gamma - 1) < \frac{1}{2}$, and hence vanishes in the limit. This demonstrates that realistic scale-free topologies intrinsically regularize causal discovery, reducing variability in orientation error. These finite-dimension results provide the first dimension-adaptive, faithfulness-robust guarantees for causal structure recovery, and challenge the intuition that high dimensionality and network heterogeneity necessarily hinder accurate discovery. Our simulation results corroborate these theoretical predictions, showing that the FNR indeed concentrates and often vanishes in practice as dimensionality grows.