On Open-Universe Causal Reasoning

Duligur Ibeling, Thomas Icard
Proceedings of The 35th Uncertainty in Artificial Intelligence Conference, PMLR 115:1233-1243, 2020.

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 this Paper

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.} }
Endnote
%0 Conference Paper %T On Open-Universe Causal Reasoning %A Duligur Ibeling %A Thomas Icard %B Proceedings of The 35th Uncertainty in Artificial Intelligence Conference %C Proceedings of Machine Learning Research %D 2020 %E Ryan P. Adams %E Vibhav Gogate %F pmlr-v115-ibeling20a %I PMLR %P 1233--1243 %U https://proceedings.mlr.press/v115/ibeling20a.html %V 115 %X 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.
APA
Ibeling, D. & Icard, T.. (2020). On Open-Universe Causal Reasoning. Proceedings of The 35th Uncertainty in Artificial Intelligence Conference, in Proceedings of Machine Learning Research 115:1233-1243 Available from https://proceedings.mlr.press/v115/ibeling20a.html.

Related Material