Estimating large causal polytrees from small samples

TL;DR

This paper introduces an algorithm capable of accurately estimating large causal polytrees from small samples, addressing challenges in high-dimensional causal inference like gene regulatory networks.

Contribution

The paper presents a novel algorithm for recovering large causal polytrees from limited data with minimal assumptions, advancing causal structure learning in high-dimensional settings.

Findings

High accuracy in causal polytree recovery from small samples

Operates under mild non-degeneracy conditions

Applicable to large-scale problems like gene networks

Abstract

We consider the problem of estimating a large causal polytree from a relatively small i.i.d. sample. This is motivated by the problem of determining causal structure when the number of variables is very large compared to the sample size, such as in gene regulatory networks. We give an algorithm that recovers the tree with high accuracy in such settings. The algorithm works under essentially no distributional or modeling assumptions other than some mild non-degeneracy conditions.