UAI 2019poster16 citations
On Open-Universe Causal Reasoning
Abstract
We extend two kinds of causal models, structural equation models and simulation models, to infinite variable spaces. This enables a semantics of counterfactuals, calculus of intervention, and axiomatization of causal reasoning for rich, expressive generative models—including those in which a causal representation exists only implicitly—in an open-universe setting. Further, we show that under suitable restrictions the two kinds of models are equivalent, perhaps surprisingly since their conditional logics differ substantially in the general case. We give a series of complete axiomatizations in which the open-universe nature of the setting is seen to be essential.
BibTeX
@InProceedings{pmlr-v115-ibeling20a,
title = {On Open-Universe Causal Reasoning},
author = {Ibeling, Duligur and Icard, Thomas},
booktitle = {Proceedings of The 35th Uncertainty in Artificial Intelligence Conference},
pages = {1233--1243},
year = {2020},
editor = {Adams, Ryan P. and Gogate, Vibhav},
volume = {115},
series = {Proceedings of Machine Learning Research},
month = {22--25 Jul},
publisher = {PMLR},
pdf = {http://proceedings.mlr.press/v115/ibeling20a/ibeling20a.pdf},
url = {https://proceedings.mlr.press/v115/ibeling20a.html},
abstract = {We extend two kinds of causal models, structural equation models and simulation models, to infinite variable spaces. This enables a semantics of counterfactuals, calculus of intervention, and axiomatization of causal reasoning for rich, expressive generative models—including those in which a causal representation exists only implicitly—in an open-universe setting. Further, we show that under suitable restrictions the two kinds of models are equivalent, perhaps surprisingly since their conditional logics differ substantially in the general case. We give a series of complete axiomatizations in which the open-universe nature of the setting is seen to be essential.}
}