Cargando…

Adversarial Neural Network-based data-simulation corrections for jet-tagging at CMS

Variable-dependent scale factors are commonly used in HEP to improve shape agreement of data and simulation. The choice of the underlying model is of great importance, but often requires a lot of manual tuning e.g. of bin sizes or fitted functions. This can be alleviated through the use of neural ne...

Descripción completa

Detalles Bibliográficos
Autor principal: Fischer, Benjamin
Lenguaje:eng
Publicado: 2019
Materias:
Acceso en línea:http://cds.cern.ch/record/2797733
_version_ 1780972424208056320
author Fischer, Benjamin
author_facet Fischer, Benjamin
author_sort Fischer, Benjamin
collection CERN
description Variable-dependent scale factors are commonly used in HEP to improve shape agreement of data and simulation. The choice of the underlying model is of great importance, but often requires a lot of manual tuning e.g. of bin sizes or fitted functions. This can be alleviated through the use of neural networks and their inherent powerful data modeling capabilities. We present a novel and generalized method for producing scale factors using an adversarial neural network. This method is investigated in the context of the bottom-quark jet-tagging algorithms within the CMS experiment. The primary network uses the jet variables as inputs to derive the scale factor for a single jet. It is trained through the use of a second network, the adversary, which aims to differentiate between the data and rescaled simulation.
id cern-2797733
institution Organización Europea para la Investigación Nuclear
language eng
publishDate 2019
record_format invenio
spelling cern-27977332021-12-13T20:15:45Zhttp://cds.cern.ch/record/2797733engFischer, BenjaminAdversarial Neural Network-based data-simulation corrections for jet-tagging at CMSDetectors and Experimental TechniquesVariable-dependent scale factors are commonly used in HEP to improve shape agreement of data and simulation. The choice of the underlying model is of great importance, but often requires a lot of manual tuning e.g. of bin sizes or fitted functions. This can be alleviated through the use of neural networks and their inherent powerful data modeling capabilities. We present a novel and generalized method for producing scale factors using an adversarial neural network. This method is investigated in the context of the bottom-quark jet-tagging algorithms within the CMS experiment. The primary network uses the jet variables as inputs to derive the scale factor for a single jet. It is trained through the use of a second network, the adversary, which aims to differentiate between the data and rescaled simulation.CMS-CR-2019-050oai:cds.cern.ch:27977332019-05-05
spellingShingle Detectors and Experimental Techniques
Fischer, Benjamin
Adversarial Neural Network-based data-simulation corrections for jet-tagging at CMS
title Adversarial Neural Network-based data-simulation corrections for jet-tagging at CMS
title_full Adversarial Neural Network-based data-simulation corrections for jet-tagging at CMS
title_fullStr Adversarial Neural Network-based data-simulation corrections for jet-tagging at CMS
title_full_unstemmed Adversarial Neural Network-based data-simulation corrections for jet-tagging at CMS
title_short Adversarial Neural Network-based data-simulation corrections for jet-tagging at CMS
title_sort adversarial neural network-based data-simulation corrections for jet-tagging at cms
topic Detectors and Experimental Techniques
url http://cds.cern.ch/record/2797733
work_keys_str_mv AT fischerbenjamin adversarialneuralnetworkbaseddatasimulationcorrectionsforjettaggingatcms