Learning causal structures using regression invariance

Amir Emad Ghassami, Saber Salehkaleybar, Negar Kiyavash, Kun Zhang

Research output: Contribution to journalConference article

Abstract

We study causal discovery in a multi-environment setting, in which the functional relations for producing the variables from their direct causes remain the same across environments, while the distribution of exogenous noises may vary. We introduce the idea of using the invariance of the functional relations of the variables to their causes across a set of environments for structure learning. We define a notion of completeness for a causal inference algorithm in this setting and prove the existence of such algorithm by proposing the baseline algorithm. Additionally, we present an alternate algorithm that has significantly improved computational and sample complexity compared to the baseline algorithm. Experiment results show that the proposed algorithm outperforms the other existing algorithms.

Original languageEnglish (US)
Pages (from-to)3012-3022
Number of pages11
JournalAdvances in Neural Information Processing Systems
Volume2017-December
StatePublished - Jan 1 2017
Event31st Annual Conference on Neural Information Processing Systems, NIPS 2017 - Long Beach, United States
Duration: Dec 4 2017Dec 9 2017

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Information Systems
  • Signal Processing

Fingerprint Dive into the research topics of 'Learning causal structures using regression invariance'. Together they form a unique fingerprint.

  • Cite this

    Ghassami, A. E., Salehkaleybar, S., Kiyavash, N., & Zhang, K. (2017). Learning causal structures using regression invariance. Advances in Neural Information Processing Systems, 2017-December, 3012-3022.