Group Invariance Principles for Causal Generative Models

Michel Besserve, Naji Shajarisales, Bernhard Schölkopf, Dominik Janzing
Proceedings of the Twenty-First International Conference on Artificial Intelligence and Statistics, PMLR 84:557-565, 2018.

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v84-besserve18a, title = {Group Invariance Principles for Causal Generative Models}, author = {Besserve, Michel and Shajarisales, Naji and Schölkopf, Bernhard and Janzing, Dominik}, booktitle = {Proceedings of the Twenty-First International Conference on Artificial Intelligence and Statistics}, pages = {557--565}, year = {2018}, editor = {Storkey, Amos and Perez-Cruz, Fernando}, volume = {84}, series = {Proceedings of Machine Learning Research}, month = {09--11 Apr}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v84/besserve18a/besserve18a.pdf}, url = {https://proceedings.mlr.press/v84/besserve18a.html}, 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.} }
Endnote
%0 Conference Paper %T Group Invariance Principles for Causal Generative Models %A Michel Besserve %A Naji Shajarisales %A Bernhard Schölkopf %A Dominik Janzing %B Proceedings of the Twenty-First International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2018 %E Amos Storkey %E Fernando Perez-Cruz %F pmlr-v84-besserve18a %I PMLR %P 557--565 %U https://proceedings.mlr.press/v84/besserve18a.html %V 84 %X 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.
APA
Besserve, M., Shajarisales, N., Schölkopf, B. & Janzing, D.. (2018). Group Invariance Principles for Causal Generative Models. Proceedings of the Twenty-First International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 84:557-565 Available from https://proceedings.mlr.press/v84/besserve18a.html.

Related Material