Conference Paper 2018

Group invariance principles for causal generative models

{The postulate of independence of cause and mechanism (ICM) has recently led to several new causal discovery algorithms. The interpretation of independence and the way it is utilized, however, varies across these methods. Our aim in this paper is to propose a group theoretic framework for ICM to unify and generalize these approaches. In our setting, the cause-mechanism relationship is assessed by perturbing it with random group transformations. We show that the group theoretic view encompasses previous ICM approaches and provides a very general tool to study the structure of data generating mechanisms with direct applications to machine learning.}

Author(s): Besserve, M and Shajarisales, N and Schölkopf, B and Janzing, D
Book Title: International Conference on Artificial Intelligence and Statistics, 9-11 April 2018, Playa Blanca, Lanzarote, Canary Islands
Volume: 84
Pages: 557--565
Year: 2018
Series: {PMLR Proceedings of Machine Learning Research}
Publisher: International Machine Learning Society
Bibtex Type: Conference Paper (inproceedings)
Address: Playa Blanca, Spain
Electronic Archiving: grant_archive

BibTex

@inproceedings{BesserveSSJ2018,
  title = {{Group invariance principles for causal generative models}},
  booktitle = {{International Conference on Artificial Intelligence and Statistics, 9-11 April 2018, Playa Blanca, Lanzarote, Canary Islands}},
  abstract = {{The postulate of independence of cause and mechanism (ICM) has recently led to several new causal discovery algorithms. The interpretation of independence and the way it is utilized, however, varies across these methods. Our aim in this paper is to propose a group theoretic framework for ICM to unify and generalize these approaches. In our setting, the cause-mechanism relationship is assessed by perturbing it with random group transformations. We show that the group theoretic view encompasses previous ICM approaches and provides a very general tool to study the structure of data generating mechanisms with direct applications to machine learning.}},
  volume = {84},
  pages = {557--565},
  series = {{PMLR Proceedings of Machine Learning Research}},
  publisher = {International Machine Learning Society},
  address = {Playa Blanca, Spain},
  year = {2018},
  slug = {besservessj2018},
  author = {Besserve, M and Shajarisales, N and Sch\"olkopf, B and Janzing, D}
}