Nested Counterfactual Identification from Arbitrary Surrogate Experiments

Authors: Juan Correa, Sanghack Lee, Elias Bareinboim

NeurIPS 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical In this paper, we study the identification of nested counterfactuals from an arbitrary combination of observations and experiments. Specifically, building on a more explicit definition of nested counterfactuals, we prove the counterfactual unnesting theorem (CUT), which allows one to map arbitrary nested counterfactuals to unnested ones. Second, we introduce a sufficient and necessary graphical condition for counterfactual identification from an arbitrary combination of observational and experimental distributions. Lastly, we develop an efficient and complete algorithm for identifying nested counterfactuals; failure of the algorithm returning an expression for a query implies it is not identifiable.
Researcher Affiliation Academia Juan D. Correa Columbia University jdcorrea@cs.columbia.edu Sanghack Lee Seoul National University sanghack@snu.ac.kr Elias Bareinboim Columbia University eb@cs.columbia.edu
Pseudocode Yes Algorithm 1 CTFIDU(Y , y , Z, G) and Algorithm 2 CTFID(Y , y , X , x , Z, G)
Open Source Code No The paper does not provide a statement or link for open-source code specific to the methodology described. It references a technical report [5] but does not explicitly state code availability.
Open Datasets No This is a theoretical paper focusing on identifiability conditions and algorithms, not on empirical studies with datasets. Therefore, no training data or access information is provided.
Dataset Splits No This is a theoretical paper, and thus it does not mention validation dataset splits.
Hardware Specification No The paper describes theoretical concepts and algorithms, not empirical experiments that would require hardware specifications.
Software Dependencies No The paper is theoretical and does not specify software dependencies with version numbers, as it does not report on empirical experiments.
Experiment Setup No The paper is theoretical and focuses on algorithms and mathematical proofs, not on specific experimental setups or hyperparameter values.