Bias and Priors in Machine Learning Calibrations for High Energy Physics

TL;DR

This paper investigates the prior dependence in machine learning calibration methods for high-energy physics, highlighting biases introduced by training sample spectra and proposing a Gaussian Ansatz approach to mitigate these issues.

Contribution

The paper explicitly analyzes prior dependence in ML calibration strategies and introduces a Gaussian Ansatz method to reduce biases in simulation-based calibration.

Findings

Simulation-based calibration can inherit training sample biases.

Gaussian Ansatz approach reduces prior dependence.

Data-based calibration remains an open challenge.

Abstract

Machine learning offers an exciting opportunity to improve the calibration of nearly all reconstructed objects in high-energy physics detectors. However, machine learning approaches often depend on the spectra of examples used during training, an issue known as prior dependence. This is an undesirable property of a calibration, which needs to be applicable in a variety of environments. The purpose of this paper is to explicitly highlight the prior dependence of some machine learning-based calibration strategies. We demonstrate how some recent proposals for both simulation-based and data-based calibrations inherit properties of the sample used for training, which can result in biases for downstream analyses. In the case of simulation-based calibration, we argue that our recently proposed Gaussian Ansatz approach can avoid some of the pitfalls of prior dependence, whereas prior-independent data-based calibration remains an open problem.