Discovering Cyclic Causal Models by Independent Components Analysis
Abstract
We generalize Shimizu et al's (2006) ICA-based approach for discovering linear non-Gaussian acyclic (LiNGAM) Structural Equation Models (SEMs) from causally sufficient, continuous-valued observational data. By relaxing the assumption that the generating SEM's graph is acyclic, we solve the more general problem of linear non-Gaussian (LiNG) SEM discovery. LiNG discovery algorithms output the distribution equivalence class of SEMs which, in the large sample limit, represents the population distribution. We apply a LiNG discovery algorithm to simulated data. Finally, we give sufficient conditions under which only one of the SEMs in the output class is 'stable'.
Keywords
Cite
@article{arxiv.1206.3273,
title = {Discovering Cyclic Causal Models by Independent Components Analysis},
author = {Gustavo Lacerda and Peter L. Spirtes and Joseph Ramsey and Patrik O. Hoyer},
journal= {arXiv preprint arXiv:1206.3273},
year = {2012}
}
Comments
Appears in Proceedings of the Twenty-Fourth Conference on Uncertainty in Artificial Intelligence (UAI2008)