Salvato in:
Dettagli Bibliografici
Autori principali: Lieberman, Benjamin, Dahbi, Salah-Eddine, Crivellin, Andreas, Stevenson, Finn, Tripathi, Nidhi, Kumar, Mukesh, Mellado, Bruce
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2404.07822
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915028349747200
author Lieberman, Benjamin
Dahbi, Salah-Eddine
Crivellin, Andreas
Stevenson, Finn
Tripathi, Nidhi
Kumar, Mukesh
Mellado, Bruce
author_facet Lieberman, Benjamin
Dahbi, Salah-Eddine
Crivellin, Andreas
Stevenson, Finn
Tripathi, Nidhi
Kumar, Mukesh
Mellado, Bruce
contents To mitigate the model dependencies of searches for new narrow resonances at the Large Hadron Collider (LHC), semi-supervised Neural Networks (NNs) can be used. Unlike fully supervised classifiers these models introduce an additional look-elsewhere effect in the process of optimising thresholds on the response distribution. We perform a frequentist study to quantify this effect, in the form of a trials factor. As an example, we consider simulated $Zγ$ data to perform narrow resonance searches using semi-supervised NN classifiers. The results from this analysis provide substantiation that the look-elsewhere effect induced by the semi-supervised NN is under control.
format Preprint
id arxiv_https___arxiv_org_abs_2404_07822
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Trials Factor for Semi-Supervised NN Classifiers in Searches for Narrow Resonances at the LHC
Lieberman, Benjamin
Dahbi, Salah-Eddine
Crivellin, Andreas
Stevenson, Finn
Tripathi, Nidhi
Kumar, Mukesh
Mellado, Bruce
High Energy Physics - Phenomenology
To mitigate the model dependencies of searches for new narrow resonances at the Large Hadron Collider (LHC), semi-supervised Neural Networks (NNs) can be used. Unlike fully supervised classifiers these models introduce an additional look-elsewhere effect in the process of optimising thresholds on the response distribution. We perform a frequentist study to quantify this effect, in the form of a trials factor. As an example, we consider simulated $Zγ$ data to perform narrow resonance searches using semi-supervised NN classifiers. The results from this analysis provide substantiation that the look-elsewhere effect induced by the semi-supervised NN is under control.
title Trials Factor for Semi-Supervised NN Classifiers in Searches for Narrow Resonances at the LHC
topic High Energy Physics - Phenomenology
url https://arxiv.org/abs/2404.07822