On Open-Universe Causal Reasoning
Artificial Intelligence
2021-06-03 v2 Logic in Computer Science
Abstract
We extend two kinds of causal models, structural equation models and simulation models, to infinite variable spaces. This enables a semantics for conditionals founded on a 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 as their axiomatizations 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
@article{arxiv.1907.02170,
title = {On Open-Universe Causal Reasoning},
author = {Duligur Ibeling and Thomas Icard},
journal= {arXiv preprint arXiv:1907.02170},
year = {2021}
}
Comments
UAI 2019