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.
Cite
Text
Ibeling and Icard. "On Open-Universe Causal Reasoning." Uncertainty in Artificial Intelligence, 2019.Markdown
[Ibeling and Icard. "On Open-Universe Causal Reasoning." Uncertainty in Artificial Intelligence, 2019.](https://mlanthology.org/uai/2019/ibeling2019uai-openuniverse/)BibTeX
@inproceedings{ibeling2019uai-openuniverse,
title = {{On Open-Universe Causal Reasoning}},
author = {Ibeling, Duligur and Icard, Thomas},
booktitle = {Uncertainty in Artificial Intelligence},
year = {2019},
pages = {1233-1243},
volume = {115},
url = {https://mlanthology.org/uai/2019/ibeling2019uai-openuniverse/}
}