Counterfactual Analysis in Dynamic Latent State Models

Martin B Haugh, Raghav Singal
Proceedings of the 40th International Conference on Machine Learning, PMLR 202:12647-12677, 2023.

Abstract

We provide an optimization-based framework to perform counterfactual analysis in a dynamic model with hidden states. Our framework is grounded in the “abduction, action, and prediction” approach to answer counterfactual queries and handles two key challenges where (1) the states are hidden and (2) the model is dynamic. Recognizing the lack of knowledge on the underlying causal mechanism and the possibility of infinitely many such mechanisms, we optimize over this space and compute upper and lower bounds on the counterfactual quantity of interest. Our work brings together ideas from causality, state-space models, simulation, and optimization, and we apply it on a breast cancer case study. To the best of our knowledge, we are the first to compute lower and upper bounds on a counterfactual query in a dynamic latent-state model.

Cite this Paper

BibTeX
@InProceedings{pmlr-v202-haugh23a, title = {Counterfactual Analysis in Dynamic Latent State Models}, author = {Haugh, Martin B and Singal, Raghav}, booktitle = {Proceedings of the 40th International Conference on Machine Learning}, pages = {12647--12677}, year = {2023}, editor = {Krause, Andreas and Brunskill, Emma and Cho, Kyunghyun and Engelhardt, Barbara and Sabato, Sivan and Scarlett, Jonathan}, volume = {202}, series = {Proceedings of Machine Learning Research}, month = {23--29 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v202/haugh23a/haugh23a.pdf}, url = {https://proceedings.mlr.press/v202/haugh23a.html}, abstract = {We provide an optimization-based framework to perform counterfactual analysis in a dynamic model with hidden states. Our framework is grounded in the “abduction, action, and prediction” approach to answer counterfactual queries and handles two key challenges where (1) the states are hidden and (2) the model is dynamic. Recognizing the lack of knowledge on the underlying causal mechanism and the possibility of infinitely many such mechanisms, we optimize over this space and compute upper and lower bounds on the counterfactual quantity of interest. Our work brings together ideas from causality, state-space models, simulation, and optimization, and we apply it on a breast cancer case study. To the best of our knowledge, we are the first to compute lower and upper bounds on a counterfactual query in a dynamic latent-state model.} }
Endnote
%0 Conference Paper %T Counterfactual Analysis in Dynamic Latent State Models %A Martin B Haugh %A Raghav Singal %B Proceedings of the 40th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2023 %E Andreas Krause %E Emma Brunskill %E Kyunghyun Cho %E Barbara Engelhardt %E Sivan Sabato %E Jonathan Scarlett %F pmlr-v202-haugh23a %I PMLR %P 12647--12677 %U https://proceedings.mlr.press/v202/haugh23a.html %V 202 %X We provide an optimization-based framework to perform counterfactual analysis in a dynamic model with hidden states. Our framework is grounded in the “abduction, action, and prediction” approach to answer counterfactual queries and handles two key challenges where (1) the states are hidden and (2) the model is dynamic. Recognizing the lack of knowledge on the underlying causal mechanism and the possibility of infinitely many such mechanisms, we optimize over this space and compute upper and lower bounds on the counterfactual quantity of interest. Our work brings together ideas from causality, state-space models, simulation, and optimization, and we apply it on a breast cancer case study. To the best of our knowledge, we are the first to compute lower and upper bounds on a counterfactual query in a dynamic latent-state model.
APA
Haugh, M.B. & Singal, R.. (2023). Counterfactual Analysis in Dynamic Latent State Models. Proceedings of the 40th International Conference on Machine Learning, in Proceedings of Machine Learning Research 202:12647-12677 Available from https://proceedings.mlr.press/v202/haugh23a.html.

Related Material