Optimizing Observables with Machine Learning for Better Unfolding

TL;DR

This paper proposes using deep learning to optimize detector-level observables in particle physics measurements, enhancing the effectiveness of traditional unfolding algorithms by allowing more flexible, data-driven definitions at the detector level.

Contribution

It introduces a novel approach to optimize detector-level observables with machine learning, improving measurement accuracy without altering the physical particle-level definitions.

Findings

Deep learning can effectively optimize detector-level observables.

Optimized observables improve unfolding performance.

Method enhances measurement precision in particle physics.

Abstract

Most measurements in particle and nuclear physics use matrix-based unfolding algorithms to correct for detector effects. In nearly all cases, the observable is defined analogously at the particle and detector level. We point out that while the particle-level observable needs to be physically motivated to link with theory, the detector-level need not be and can be optimized. We show that using deep learning to define detector-level observables has the capability to improve the measurement when combined with standard unfolding methods.