Cargando…

Learning New Physics from an Imperfect Machine

We show how to deal with uncertainties on the Standard Model predictions in an agnostic new physics search strategy that exploits artificial neural networks. Our approach builds directly on the specific Maximum Likelihood ratio treatment of uncertainties as nuisance parameters for hypothesis testing...

Descripción completa

Detalles Bibliográficos
Autores principales: d'Agnolo, Raffaele Tito, Grosso, Gaia, Pierini, Maurizio, Wulzer, Andrea, Zanetti, Marco
Lenguaje:eng
Publicado: 2021
Materias:
Acceso en línea:https://dx.doi.org/10.1140/epjc/s10052-022-10226-y
http://cds.cern.ch/record/2791774
_version_ 1780972327052247040
author d'Agnolo, Raffaele Tito
Grosso, Gaia
Pierini, Maurizio
Wulzer, Andrea
Zanetti, Marco
author_facet d'Agnolo, Raffaele Tito
Grosso, Gaia
Pierini, Maurizio
Wulzer, Andrea
Zanetti, Marco
author_sort d'Agnolo, Raffaele Tito
collection CERN
description We show how to deal with uncertainties on the Standard Model predictions in an agnostic new physics search strategy that exploits artificial neural networks. Our approach builds directly on the specific Maximum Likelihood ratio treatment of uncertainties as nuisance parameters for hypothesis testing that is routinely employed in high-energy physics. After presenting the conceptual foundations of our method, we first illustrate all aspects of its implementation and extensively study its performances on a toy one-dimensional problem. We then show how to implement it in a multivariate setup by studying the impact of two typical sources of experimental uncertainties in two-body final states at the LHC.
id cern-2791774
institution Organización Europea para la Investigación Nuclear
language eng
publishDate 2021
record_format invenio
spelling cern-27917742023-08-19T02:40:27Zdoi:10.1140/epjc/s10052-022-10226-yhttp://cds.cern.ch/record/2791774engd'Agnolo, Raffaele TitoGrosso, GaiaPierini, MaurizioWulzer, AndreaZanetti, MarcoLearning New Physics from an Imperfect Machinehep-phParticle Physics - PhenomenologyWe show how to deal with uncertainties on the Standard Model predictions in an agnostic new physics search strategy that exploits artificial neural networks. Our approach builds directly on the specific Maximum Likelihood ratio treatment of uncertainties as nuisance parameters for hypothesis testing that is routinely employed in high-energy physics. After presenting the conceptual foundations of our method, we first illustrate all aspects of its implementation and extensively study its performances on a toy one-dimensional problem. We then show how to implement it in a multivariate setup by studying the impact of two typical sources of experimental uncertainties in two-body final states at the LHC.We show how to deal with uncertainties on the Standard Model predictions in an agnostic new physics search strategy that exploits artificial neural networks. Our approach builds directly on the specific Maximum Likelihood ratio treatment of uncertainties as nuisance parameters for hypothesis testing that is routinely employed in high-energy physics. After presenting the conceptual foundations of our method, we first illustrate all aspects of its implementation and extensively study its performances on a toy one-dimensional problem. We then show how to implement it in a multivariate setup by studying the impact of two typical sources of experimental uncertainties in two-body final states at the LHC.arXiv:2111.13633oai:cds.cern.ch:27917742021-11-26
spellingShingle hep-ph
Particle Physics - Phenomenology
d'Agnolo, Raffaele Tito
Grosso, Gaia
Pierini, Maurizio
Wulzer, Andrea
Zanetti, Marco
Learning New Physics from an Imperfect Machine
title Learning New Physics from an Imperfect Machine
title_full Learning New Physics from an Imperfect Machine
title_fullStr Learning New Physics from an Imperfect Machine
title_full_unstemmed Learning New Physics from an Imperfect Machine
title_short Learning New Physics from an Imperfect Machine
title_sort learning new physics from an imperfect machine
topic hep-ph
Particle Physics - Phenomenology
url https://dx.doi.org/10.1140/epjc/s10052-022-10226-y
http://cds.cern.ch/record/2791774
work_keys_str_mv AT dagnoloraffaeletito learningnewphysicsfromanimperfectmachine
AT grossogaia learningnewphysicsfromanimperfectmachine
AT pierinimaurizio learningnewphysicsfromanimperfectmachine
AT wulzerandrea learningnewphysicsfromanimperfectmachine
AT zanettimarco learningnewphysicsfromanimperfectmachine