Causal structure learning from time series: Large regression coefficients may predict causal links better in practice than small p-values

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

Documents

In this article, we describe the algorithms for causal structure learning from time series data that won the Causality 4 Climate competition at the Conference on Neural Information Processing Systems 2019 (NeurIPS). We examine how our combination of established ideas achieves competitive performance on semi-realistic and realistic time series data exhibiting common challenges in real-world Earth sciences data. In particular, we discuss a) a rationale for leveraging linear methods to identify causal links in non-linear systems, b) a simulation-backed explanation as to why large regression coefficients may predict causal links better in practice than small p-values and thus why normalising the data may sometimes hinder causal structure learning. For benchmark usage, we detail the algorithms here and provide implementations at {https://github.com/sweichwald/tidybench}. We propose the presented competition-proven methods for baseline benchmark comparisons to guide the development of novel algorithms for structure learning from time series.
Original languageEnglish
Title of host publicationProceedings of the NeurIPS 2019 Competition and Demonstration Track
PublisherPMLR
Publication date2020
Pages27-36
Publication statusPublished - 2020
EventNeural Information Processing Systems Conference 2019, - Vancouver, Canada
Duration: 8 Dec 201914 Dec 2019

Conference

ConferenceNeural Information Processing Systems Conference 2019,
LandCanada
ByVancouver
Periode08/12/201914/12/2019
SeriesProceedings of Machine Learning Research
Volume123
ISSN1938-7228

Number of downloads are based on statistics from Google Scholar and www.ku.dk


No data available

ID: 248233218