Utilize este identificador para referenciar este registo:
https://hdl.handle.net/1822/74961
Registo completo
Campo DC | Valor | Idioma |
---|---|---|
dc.contributor.author | Crispim Romão, M. | por |
dc.contributor.author | Castro, Nuno Filipe | por |
dc.contributor.author | Pedro, R. | por |
dc.date.accessioned | 2021-12-14T15:37:18Z | - |
dc.date.available | 2021-12-14T15:37:18Z | - |
dc.date.issued | 2021-01-15 | - |
dc.identifier.citation | Crispim Romão, M., Castro, N.F. & Pedro, R. Finding new physics without learning about it: anomaly detection as a tool for searches at colliders. Eur. Phys. J. C 81, 27 (2021). https://doi.org/10.1140/epjc/s10052-020-08807-w | por |
dc.identifier.issn | 1434-6044 | - |
dc.identifier.uri | https://hdl.handle.net/1822/74961 | - |
dc.description.abstract | In this paper we propose a new strategy, based on anomaly detection methods, to search for new physics phenomena at colliders independently of the details of such new events. For this purpose, machine learning techniques are trained using Standard Model events, with the corresponding outputs being sensitive to physics beyond it. We explore three novel AD methods in HEP: Isolation Forest, Histogram-Based Outlier Detection, and Deep Support Vector Data Description; alongside the most customary Autoencoder. In order to evaluate the sensitivity of the proposed approach, predictions from specific new physics models are considered and compared to those achieved when using fully supervised deep neural networks. A comparison between shallow and deep anomaly detection techniques is also presented. Our results demonstrate the potential of semi-supervised anomaly detection techniques to extensively explore the present and future hadron colliders' data. | por |
dc.description.sponsorship | We thank Guilherme Milhano, Maria Ramos and Guilherme Guedes for the careful reading of the manuscript and for the useful discussions. We also thank Ana Peixoto and Tiago Vale for providing the MadGraph cards used for the simulation of the beyond the Standard Model samples. We acknowledge the support from FCT Portugal, Lisboa2020, Compete2020, Portugal2020 and FEDER under project PTDC/FIS-PAR/29147/2017. The computational part of this work was supported by INCD (funded by FCT and FEDER under the project 01/SAICT/2016 nr. 022153) and by the Minho Advanced Computing Center (MACC). The Titan Xp GPU card used for the training of the Deep Neural Networks developed for this project was kindly donated by the NVIDIA Corporation. | por |
dc.language.iso | eng | por |
dc.publisher | Springer | por |
dc.relation | PTDC/FIS-PAR/29147/2017 | por |
dc.rights | openAccess | por |
dc.rights.uri | http://creativecommons.org/licenses/by/4.0/ | por |
dc.title | Finding new physics without learning about it: anomaly detection as a tool for searches at colliders | por |
dc.type | article | por |
dc.peerreviewed | yes | por |
oaire.citationIssue | 1 | por |
oaire.citationVolume | 81 | por |
dc.date.updated | 2021-12-07T14:36:46Z | - |
dc.identifier.doi | 10.1140/epjc/s10052-020-08807-w | por |
dc.subject.wos | Science & Technology | - |
sdum.export.identifier | 11009 | - |
sdum.journal | European Physical Journal C | por |
Aparece nas coleções: | LIP - Artigos/papers |
Ficheiros deste registo:
Ficheiro | Descrição | Tamanho | Formato | |
---|---|---|---|---|
Crispim_Romao_2021_Article_Finding_New_Physics_Without_Learning.pdf | 6,76 MB | Adobe PDF | Ver/Abrir |
Este trabalho está licenciado sob uma Licença Creative Commons