Estimation rates for sparse linear cyclic causal models
Author(s)
Hütter, JC; Rigollet, P
DownloadPublished version (1.608Mb)
Publisher Policy
Publisher Policy
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Terms of use
Metadata
Show full item recordAbstract
© Proceedings of the 36th Conference on Uncertainty in Artificial Intelligence, UAI 2020. All rights reserved. Causal models are fundamental tools to understand complex systems and predict the effect of interventions on such systems. However, despite an extensive literature in the population-or infinite-sample-case, where distributions are assumed to be known, little is known about the statistical rates of convergence of various methods, even for the simplest models. In this work, allowing for cycles, we study linear structural equations models with homoscedastic Gaussian noise and in the presence of interventions that make the model identifiable. More specifically, we present statistical rates of estimation for both the LLC estimator introduced by Hyttinen, Eberhardt and Hoyer and a novel two-step penalized maximum likelihood estimator. We establish asymptotic near minimax optimality for the maximum likelihood estimator over a class of sparse causal graphs in the case of near-optimally chosen interventions. Moreover, we find evidence for practical advantages of this estimator compared to LLC in synthetic numerical experiments.
Date issued
2020Department
Massachusetts Institute of Technology. Department of MathematicsJournal
Proceedings of the 36th Conference on Uncertainty in Artificial Intelligence, UAI 2020
Citation
Hütter, JC and Rigollet, P. 2020. "Estimation rates for sparse linear cyclic causal models." Proceedings of the 36th Conference on Uncertainty in Artificial Intelligence, UAI 2020.
Version: Final published version