AISTATS 2018poster0 citations
Group Invariance Principles for Causal Generative Models
Michel Besserve, Naji Shajarisales, Bernhard Schölkopf, Dominik Janzing
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.
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.}
}