A Fast Non-parametric Approach for Local Causal Structure Learning

TL;DR

DAG-FOCI is a fast, non-parametric algorithm for local causal structure learning that makes minimal assumptions and provides theoretical guarantees, demonstrated on biological data.

Contribution

It introduces DAG-FOCI, a novel algorithm for causal structure learning that is computationally efficient and theoretically supported under minimal assumptions.

Findings

Effective on simulated data

Successfully applied to biological dataset

Provides theoretical guarantees

Abstract

We study the problem of causal structure learning with essentially no assumptions on the functional relationships and noise. We develop DAG-FOCI, a computationally fast algorithm for this setting that is based on the FOCI variable selection algorithm in~\cite{azadkia2021simple}. DAG-FOCI outputs the set of parents of a response variable of interest. We provide theoretical guarantees of our procedure when the underlying graph does not contain any (undirected) cycle containing the response variable of interest. Furthermore, in the absence of this assumption, we give a conservative guarantee against false positive causal claims when the set of parents is identifiable. We demonstrate the applicability of DAG-FOCI on simulated as well as a real dataset from computational biology~\cite{sachs2005causal}.