A Caltech Library Service

Approximate Causal Abstraction

Beckers, Sander and Eberhardt, Frederick and Halpern, Joseph Y. (2019) Approximate Causal Abstraction. Proceedings of Machine Learning Research, 115 . pp. 606-615. ISSN 2640-3498.

[img] PDF - Published Version
See Usage Policy.

[img] PDF - Submitted Version
See Usage Policy.

[img] PDF - Supplemental Material
See Usage Policy.


Use this Persistent URL to link to this item:


Scientific models describe natural phenomena at different levels of abstraction. Abstract descriptions can provide the basis for interventions on the system and explanation of observed phenomena at a level of granularity that is coarser than the most fundamental account of the system. Beckers and Halpern (2019), building on prior work of Rubinstein et al. (2017), developed an account of abstraction for causal models that is exact. Here we extend this account to the more realistic case where an abstract causal model only offers an approximation of the underlying system. We show how the resulting account handles the discrepancy that can arise between low- and high-level causal models of the same system, and in the process provide an account of how one causal model approximates another, a topic of independent interest. Finally, we extend the account of approximate abstractions to probabilistic causal models, indicating how and where uncertainty can enter into an approximate abstraction.

Item Type:Article
Related URLs:
URLURL TypeDescription Paper
Alternate Title:Approximate Causal Abstractions
Additional Information:© The authors and PMLR 2021. ML Research Press. Beckers was supported by the grant ERC-2013-CoG project REINS 616512. Eberhardt was supported in part by NSF grants 1564330 and BCS-1845958, and HRGC grant 13601017. Halpern was supported in part by NSF grants IIS-1703846 and IIS-1718108, ARO grant W911NF-17-1-0592, and a grant from the Open Philanthropy project. We thank the UAI reviewers for many useful comments.
Funding AgencyGrant Number
European Research Council (ERC)616512
Army Research Office (ARO)W911NF-17-1-0592
Open Philanthropy ProjectUNSPECIFIED
Record Number:CaltechAUTHORS:20200527-100350364
Persistent URL:
Official Citation:Beckers, S., Eberhardt, F., Halpern, J.Y. (2020). Approximate Causal Abstractions. Proceedings of The 35th Uncertainty in Artificial Intelligence Conference, in Proceedings of Machine Learning Research. 115:606-615
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:103488
Deposited By: Tony Diaz
Deposited On:27 May 2020 17:16
Last Modified:09 Mar 2022 22:36

Repository Staff Only: item control page