MCNNTUNES: Tuning Shower Monte Carlo generators with machine learning

The parameters tuning of event generators is a research topic characterized by complex choices: the generator response to parameter variations is difficult to obtain on a theoretical basis, and numerical methods are hardly tractable due to the long computational times required by generators. Event generator tuning has been tackled by parametrization-based techniques, with the most successful one being a polynomial parametrization. In this work, an implementation of tuning procedures based on artificial neural networks is proposed. The implementation was tested with closure testing and experimental measurements from the ATLAS experiment at the Large Hadron Collider. Program summary Program Title: MCNNTUNES CPC Library link to program files: https://doi.org/10.17632/dmkydsxgd3.1 Developer's repository link: https://github.com/N3PDF/mcnntunes Licensing provisions: GPLv3 Programming language: Python Nature of problem: Shower Monte Carlo generators introduce many parameters that must be tuned to reproduce the experimental measurements. The dependence of the generator output on these parameters is difficult to obtain on a theoretical basis. Solution method: Implementation of a tuning method using supervised machine learning algorithms based on neural networks, which are universal approximators. (C) 2021 Elsevier B.V. All rights reserved.

Automated summary

The research discusses a tuning method for event generators using artificial neural networks, which is validated through closure testing and experimental measurements.