DeepAI AI Chat
Log In Sign Up

Bias and Priors in Machine Learning Calibrations for High Energy Physics

05/10/2022
by   Rikab Gambhir, et al.
MIT
Berkeley Lab
0

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.

READ FULL TEXT

page 8

page 12

09/30/2022

Variable-Based Calibration for Machine Learning Classifiers

The deployment of machine learning classifiers in high-stakes domains re...
11/19/2020

Continuous calibration of a digital twin: comparison of particle filter and Bayesian calibration approaches

Assimilation of continuously streamed monitored data is an essential com...
10/18/2022

Generative models uncertainty estimation

In recent years fully-parametric fast simulation methods based on genera...
07/17/2022

Uncertainty Calibration in Bayesian Neural Networks via Distance-Aware Priors

As we move away from the data, the predictive uncertainty should increas...
03/10/2023

Machine learning for sports betting: should forecasting models be optimised for accuracy or calibration?

Sports betting's recent federal legalisation in the USA coincides with t...
10/31/2021

PnPOOD : Out-Of-Distribution Detection for Text Classification via Plug andPlay Data Augmentation

While Out-of-distribution (OOD) detection has been well explored in comp...
09/27/2021

A Priori Calibration of Transient Kinetics Data via Machine Learning

The temporal analysis of products reactor provides a vast amount of tran...