CaltechAUTHORS
  A Caltech Library Service

Causal Discovery from Subsampled Time Series Data by Constraint Optimization

Hyttinen, Antti and Plis, Sergey and Järvisalo, Matti and Eberhardt, Frederick and Danks, David (2016) Causal Discovery from Subsampled Time Series Data by Constraint Optimization. In: JMLR: Workshop and Conference Proceedings. Vol.52. , Cambridge, MA, pp. 216-227. ISBN 1938-7288. PMCID PMC5305170. http://resolver.caltech.edu/CaltechAUTHORS:20170221-090923083

[img] PDF - Published Version
See Usage Policy.

767Kb
[img] PDF - Submitted Version
See Usage Policy.

875Kb

Use this Persistent URL to link to this item: http://resolver.caltech.edu/CaltechAUTHORS:20170221-090923083

Abstract

This paper focuses on causal structure estimation from time series data in which measurements are obtained at a coarser timescale than the causal timescale of the underlying system. Previous work has shown that such subsampling can lead to significant errors about the system’s causal structure if not properly taken into account. In this paper, we first consider the search for the system timescale causal structures that correspond to a given measurement timescale structure. We provide a constraint satisfaction procedure whose computational performance is several orders of magnitude better than previous approaches. We then consider finite-sample data as input, and propose the first constraint optimization approach for recovering the system timescale causal structure. This algorithm optimally recovers from possible conflicts due to statistical errors. More generally, these advances allow for a robust and non-parametric estimation of system timescale causal structures from subsampled time series data.


Item Type:Book Section
Related URLs:
URLURL TypeDescription
http://www.jmlr.org/proceedings/papers/v52/hyttinen16.htmlPublisherArticle
https://arxiv.org/abs/1602.07970arXivDiscussion paper
https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5305170/PubMed CentralArticle
Additional Information:© 2016 JMLR. AH was supported by Academy of Finland Centre of Excellence in Computational Inference Research COIN (grant 251170). SP was supported by NSF IIS-1318759 & NIH R01EB005846. MJ was supported by Academy of Finland Centre of Excellence in Computational Inference Research COIN (grant 251170) and grants 276412, 284591; and Research Funds of the University of Helsinki. FE was supported by NSF 1564330. DD was supported by NSF IIS-1318815 &NIH U54HG008540 (from the National Human Genome Research Institute through funds provided by the trans-NIH Big Data to Knowledge (BD2K) initiative). The content is solely the responsibility of the authors and does not necessarily represent the official views of the National Institutes of Health.
Funders:
Funding AgencyGrant Number
Academy of Finland251170
NSFIIS-1318759
NIHR01EB005846
Academy of Finland276412
Academy of Finland284591
University of HelsinkiUNSPECIFIED
NSFIIS-1564330
NSFIIS-1318815
NIHU54HG008540
National Human Genome Research InstituteUNSPECIFIED
Trans-NIH Big Data to Knowledge (BD2K) InitiativeUNSPECIFIED
Subject Keywords:causality; causal discovery; graphical models; time series; constraint satisfaction; constraint optimization
PubMed Central ID:PMC5305170
Record Number:CaltechAUTHORS:20170221-090923083
Persistent URL:http://resolver.caltech.edu/CaltechAUTHORS:20170221-090923083
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:74421
Collection:CaltechAUTHORS
Deposited By: Ruth Sustaita
Deposited On:21 Feb 2017 17:45
Last Modified:22 Feb 2017 19:32

Repository Staff Only: item control page