Estimating large causal polytrees from small samples
This addresses the challenge of determining causal structure in high-dimensional, low-sample scenarios like genomics, though it appears incremental as it builds on existing polytree methods.
The paper tackles the problem of estimating large causal polytrees from small samples, such as in gene regulatory networks, and presents an algorithm that recovers the tree with high accuracy under minimal assumptions.
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.