Unknown Unknowns: Model Misspecification in Machine Learning for Physics

2026-08-13

AI Summary

This study addresses the risks of unknown unknowns arising from model misspecification in physical inverse problems by proposing an iterative diagnosis and mitigation framework. Treating misspecification as an opportunity for discovery, this work establishes a closed-loop detection-mitigation analytical paradigm that integrates complementary diagnostics, iterative updating, and robustness analysis strategies. Consequently, this research develops a systematic methodology for managing unknown unknowns, effectively enhancing model robustness against unforeseen biases and significantly improving the reliability of physical measurements. Ultimately, the proposed framework provides a novel safety assurance mechanism for solving complex inverse problems, ensuring greater confidence in computational reconstructions where model fidelity cannot be fully guaranteed a priori.

Abstract

Machine learning is now a central tool for solving inverse problems in particle physics and astronomy. Models are trained on simulation and deployed on real data, raising the question not just of whether they fit, but of whether they are wrong in ways we did not anticipate: the unknown unknowns. This challenge of model misspecification is not unique to machine learning. In physics, misspecification is sometimes exactly what we want to find: new discoveries appear as failures of existing models. At other times, we want such effects absorbed into the analysis without biasing the measurement. A robust analysis is one that absorbs the misspecifications we are not interested in, while preserving sensitivity to the ones we are. Machine learning can both amplify misspecification and provide new tools to address it. We discuss the challenges of model misspecification, diagnostics for detecting it, and strategies for mitigation. No single diagnostic can confirm that a model is correctly specified: detection and mitigation are two halves of an iterative loop, in which a battery of complementary diagnostics is applied, the model is updated, and the process repeated. Robustness against unknown unknowns is ultimately less about any single technique than about a disposition: a willingness to suspect one's own model, and to design analyses that can survive being wrong in ways one did not anticipate.

Problem

• Model Misspecification
• Unknown Unknowns
• Inverse Problems
• Machine Learning
• Robustness

Innovation

• Model Misspecification
• Unknown Unknowns
• Inverse Problems
• Robustness
• Iterative Diagnostics