English

High-Dimensional Causal Discovery Under non-Gaussianity

Methodology 2019-06-28 v3

Abstract

We consider graphical models based on a recursive system of linear structural equations. This implies that there is an ordering, σ\sigma, of the variables such that each observed variable YvY_v is a linear function of a variable specific error term and the other observed variables YuY_u with σ(u)<σ(v)\sigma(u) < \sigma (v). The causal relationships, i.e., which other variables the linear functions depend on, can be described using a directed graph. It has been previously shown that when the variable specific error terms are non-Gaussian, the exact causal graph, as opposed to a Markov equivalence class, can be consistently estimated from observational data. We propose an algorithm that yields consistent estimates of the graph also in high-dimensional settings in which the number of variables may grow at a faster rate than the number of observations, but in which the underlying causal structure features suitable sparsity; specifically, the maximum in-degree of the graph is controlled. Our theoretical analysis is couched in the setting of log-concave error distributions.

Keywords

Cite

@article{arxiv.1803.11273,
  title  = {High-Dimensional Causal Discovery Under non-Gaussianity},
  author = {Y. Samuel Wang and Mathias Drton},
  journal= {arXiv preprint arXiv:1803.11273},
  year   = {2019}
}
R2 v1 2026-06-23T01:09:20.292Z