CaltechAUTHORS
  A Caltech Library Service

Discovering cyclic causal models with latent variables: a general SAT-based procedure

Hyttinen, Antti and Hoyer, Patrik O. and Eberhardt, Frederick and Järvisalo, Matti (2013) Discovering cyclic causal models with latent variables: a general SAT-based procedure. In: UAI'13 Proceedings of the Twenty-Ninth Conference on Uncertainty in Artificial Intelligence. AUAI Press , Arlington, VA, pp. 301-310. ISBN 9780974903996. https://resolver.caltech.edu/CaltechAUTHORS:20190327-085903347

[img] PDF - Accepted Version
See Usage Policy.

421kB

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20190327-085903347

Abstract

We present a very general approach to learning the structure of causal models based on d-separation constraints, obtained from any given set of overlapping passive observational or experimental data sets. The procedure allows for both directed cycles (feedback loops) and the presence of latent variables. Our approach is based on a logical representation of causal pathways, which permits the integration of quite general background knowledge, and inference is performed using a Boolean satisfiability (SAT) solver. The procedure is complete in that it exhausts the available information on whether any given edge can be determined to be present or absent, and returns "unknown" otherwise. Many existing constraint-based causal discovery algorithms can be seen as special cases, tailored to circumstances in which one or more restricting assumptions apply. Simulations illustrate the effect of these assumptions on discovery and how the present algorithm scales.


Item Type:Book Section
Related URLs:
URLURL TypeDescription
http://arxiv.org/abs/1309.6836arXivDiscussion Paper
Additional Information:© 2013 AUAI Press. This research was supported by the Academy of Finland under grants 218147 and 255625 (POH), 132812 and 251170 (MJ), by HIIT (AH) and by the James S. McDonnell Foundation (FE).
Funders:
Funding AgencyGrant Number
Academy of Finland218147
Academy of Finland255625
Academy of Finland132812
Academy of Finland251170
University of HelsinkiUNSPECIFIED
James S. McDonnell FoundationUNSPECIFIED
Record Number:CaltechAUTHORS:20190327-085903347
Persistent URL:https://resolver.caltech.edu/CaltechAUTHORS:20190327-085903347
Official Citation:Antti Hyttinen, Patrik O. Hoyer, Frederick Eberhardt, and Matti Järvisalo. 2013. Discovering cyclic causal models with latent variables: a general SAT-based procedure. In Proceedings of the Twenty-Ninth Conference on Uncertainty in Artificial Intelligence (UAI'13), Ann Nicholson and Padhraic Smyth (Eds.). AUAI Press, Arlington, Virginia, United States, 301-310.
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:94196
Collection:CaltechAUTHORS
Deposited By: George Porter
Deposited On:27 Mar 2019 22:17
Last Modified:03 Oct 2019 21:01

Repository Staff Only: item control page