A control system framework for counterfactuals: an optimization based approach
Abstract
Counterfactuals are a concept inherited from the field of logic and in general attain to the existence of causal relations between sentences or events. In particular, this concept has been introduced also in the context of interpretability in artificial intelligence, where counterfactuals refer to the minimum change to the feature values that changes the prediction of a classification model. The artificial intelligence framework of counterfactuals is mostly focused on machine learning approaches, typically neglecting the physics of the variables that determine a change in class. However, a theoretical formulation of counterfactuals in a control system framework - i.e., able to account for the mechanisms underlying a change in class - is lacking. To fill this gap, in this work we propose an original control system, physics-informed, theoretical foundation for counterfactuals, by means of the formulation of an optimal control problem. We apply the proposed methodology to a general glucose-insulin regulation model and results appear promising and pave the way to the possible integration with artificial intelligence techniques, with the aim of feeding machine learning models with the physics knowledge acquired through the system framework.
Cite
@article{arxiv.2501.12914,
title = {A control system framework for counterfactuals: an optimization based approach},
author = {Pierluigi Francesco De Paola and Jared Miller and Alessandro Borri and Alessia Paglialonga and Fabrizio Dabbene},
journal= {arXiv preprint arXiv:2501.12914},
year = {2025}
}