UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

Conditions and Assumptions for Constraint-based Causal Structure Learning

Sadeghi, Kayvan; Soo, Terry; (2022) Conditions and Assumptions for Constraint-based Causal Structure Learning. Journal of Machine Learning Research , 23 , Article 109. Green open access

[thumbnail of Soo_21-0425.pdf]
Preview
Text
Soo_21-0425.pdf

Download (401kB) | Preview

Abstract

This paper formalizes constraint-based structure learning of the "true" causal graph from observed data when unobserved variables are also existent. We provide conditions for a "natural" family of constraint-based structure-learning algorithms that output graphs that are Markov equivalent to the causal graph. Under the faithfulness assumption, this natural family contains all exact structure-learning algorithms. More importantly, we provide clear and testable assumptions, as an alternative to faithfulness, under which any natural structure-learning algorithm outputs Markov equivalent graphs to the causal graph. We provide these definitions and results for the general class of models under the assumption that the distribution is Markovian to the true causal graph, and we specialize the definitions and results for structural causal models.

Type: Article
Title: Conditions and Assumptions for Constraint-based Causal Structure Learning
Open access status: An open access version is available from UCL Discovery
Publisher version: https://www.jmlr.org/papers/v23/21-0425.html
Language: English
Additional information: License: CC-BY 4.0, see https://creativecommons.org/licenses/by/4.0/. Attribution requirements are provided at http://jmlr.org/papers/v23/21-0425.html.
Keywords: ancestral graphs; causal discovery; constraint-based structure learning; faithfulness; structural causal models
UCL classification: UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences > Dept of Statistical Science
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL
URI: https://discovery.ucl.ac.uk/id/eprint/10144714
Downloads since deposit
11Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item