Machine learning as an instrument for data unfolding

TL;DR

This paper introduces a machine learning approach using neural networks to correct detector smearing effects in data analysis, enabling more accurate event-by-event inference of true quantities, with potential applications in high energy physics.

Contribution

It presents a novel machine learning method employing neural networks for data unfolding, allowing multiple variables to improve correction accuracy over standard techniques.

Findings

Method successfully passes closure tests in toy examples

Uses multiple reconstructed variables for improved inference

Potential for application in high energy physics data analysis

Abstract

A method for correcting for detector smearing effects using machine learning techniques is presented. Compared to the standard approaches the method can use more than one reconstructed variable to infere the value of the unsmeared quantity on event by event basis. The method is implemented using a sequential neural network with a categorical cross entropy as the loss function. It is tested on a toy example and is shown to satisfy basic closure tests. Possible application of the method for analysis of the data from high energy physics experiments is discussed.