4
IRUS Total
Downloads
  Altmetric

Counterfactual analysis in dynamic latent-state models

File Description SizeFormat 
main.pdfAccepted version635.69 kBAdobe PDFView/Open
Title: Counterfactual analysis in dynamic latent-state models
Authors: Haugh, M
Singal, R
Item Type: Conference Paper
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 predic- tion” 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 under- lying causal mechanism and the possibility of in- finitely 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.
Issue Date: 23-Jul-2023
Date of Acceptance: 24-Apr-2023
URI: http://hdl.handle.net/10044/1/109047
Publisher: MLResearchPress
Start Page: 12647
End Page: 12677
Journal / Book Title: Proceedings of Machine Learning Research
Volume: 202
Copyright Statement: © Copyright 2023 by the author(s).
Conference Name: International Conference on Machine Learning 2023
Publication Status: Published
Start Date: 2023-07-23
Finish Date: 2023-07-29
Conference Place: Hawaii, USA
Appears in Collections:Imperial College Business School