A Caltech Library Service

Stability of Causal Inference

Schulman, Leonard J. and Srivastava, Piyush (2016) Stability of Causal Inference. In: UAI 2016 - Proceedings. , Art. No. 214.

[img] PDF - Published Version
See Usage Policy.


Use this Persistent URL to link to this item:


We consider the sensitivity of causal identification to small perturbations in the input. A long line of work culminating in papers by Shpitser and Pearl (2006) and Huang and Valtorta (2008) led to a complete procedure for the causal identification problem. In our main result in this paper, we show that the identification function computed by these procedures is in some cases extremely unstable numerically. Specifically, the “condition number” of causal identification can be of the order of Ω(exp(n ^(0.49))) on an identifiable semiMarkovian model with n visible nodes. That is, in order to give an output accurate to d bits, the empirical probabilities of the observable events need to be obtained to accuracy d + Ω(n ^(0.49)) bits.

Item Type:Book Section
Related URLs:
URLURL TypeDescription of Contents
Schulman, Leonard J.0000-0001-9901-2797
Srivastava, Piyush0000-0003-0953-2890
Additional Information:This research was supported by NSF grant CCF-1319745. We thank the reviewers for helpful comments.
Funding AgencyGrant Number
Record Number:CaltechAUTHORS:20160628-152001110
Persistent URL:
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:68719
Deposited By: Joy Painter
Deposited On:28 Jun 2016 22:40
Last Modified:09 Mar 2020 13:19

Repository Staff Only: item control page