A1191
Title: Learning a directed acyclic graph with heteroscedastic errors
Authors: Chunlin Li - University of Virginia and Iowa State University (United States) [presenting]
Abstract: The purpose is to introduce a causal discovery method to learn the causal relations in a directed acyclic graph (DAG) with heteroscedastic errors. First, the model identifiability is derived for DAGs with heteroskedastic errors. Then, a new DAG reconstruction method called residual quantile (ResQ) estimation is proposed, which iteratively reconstructs the causal order of the variables. It is proven that ResQ enjoys desirable statistical properties such as reconstruction consistency in both low- and high-dimensional cases and estimation robustness to heteroskedastic/heavy-tailed/contaminated errors. The theoretical properties have been substantiated by the synthetic experiments and applications to real-world causal benchmark datasets, where ResQ compares favorably against state-of-the-art competitors.
