A control system framework for counterfactuals: an optimization based approach

TL;DR

This paper introduces a physics-informed control system framework for counterfactuals, integrating causal reasoning with physical models to enhance interpretability in AI, demonstrated through a glucose-insulin regulation example.

Contribution

It presents a novel control system approach for counterfactuals that incorporates physical laws, bridging the gap between causal reasoning and physics-based models in AI.

Findings

Promising results in glucose-insulin model application

Framework enables physics-informed counterfactual generation

Potential for integration with machine learning models

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.