Reasoning About Causal Models with Infinitely Many Variables
Abstract
Generalized structural equations models (GSEMs) (Peters and Halpern 2021), are, as the name suggests, a generalization of structural equations models (SEMs). They can deal with (among other things) infinitely many variables with infinite ranges, which is critical for capturing dynamical systems. We provide a sound and complete axiomatization of causal reasoning in GSEMs that is an extension of the sound and complete axiomatization provided by Halpern (2000) for SEMs. Considering GSEMs helps clarify what properties Halpern's axioms capture.
Cite
Text
Halpern and Peters. "Reasoning About Causal Models with Infinitely Many Variables." AAAI Conference on Artificial Intelligence, 2022. doi:10.1609/AAAI.V36I5.20508Markdown
[Halpern and Peters. "Reasoning About Causal Models with Infinitely Many Variables." AAAI Conference on Artificial Intelligence, 2022.](https://mlanthology.org/aaai/2022/halpern2022aaai-reasoning/) doi:10.1609/AAAI.V36I5.20508BibTeX
@inproceedings{halpern2022aaai-reasoning,
title = {{Reasoning About Causal Models with Infinitely Many Variables}},
author = {Halpern, Joseph Y. and Peters, Spencer},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2022},
pages = {5668-5675},
doi = {10.1609/AAAI.V36I5.20508},
url = {https://mlanthology.org/aaai/2022/halpern2022aaai-reasoning/}
}