Beyond cuts in small signal scenarios

We investigate enhancing the sensitivity of new physics searches at the LHC by machine learning in the case of background dominance and a high degree of overlap between the observables for signal and background. We use two different models, XGBoost and a deep neural network, to exploit correlations...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:The European physical journal. C, Particles and fields Jg. 83; H. 5; S. 379 - 22
Hauptverfasser: Alvestad, Daniel, Fomin, Nikolai, Kersten, Jörn, Maeland, Steffen, Strümke, Inga
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Heidelberg Springer 01.05.2023
Springer Nature B.V
SpringerOpen
Schlagworte:
ISSN:1434-6044, 1434-6052
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract We investigate enhancing the sensitivity of new physics searches at the LHC by machine learning in the case of background dominance and a high degree of overlap between the observables for signal and background. We use two different models, XGBoost and a deep neural network, to exploit correlations between observables and compare this approach to the traditional cut-and-count method. We consider different methods to analyze the models' output, finding that a template fit generally performs better than a simple cut. By means of a Shapley decomposition, we gain additional insight into the relationship between event kinematics and the machine learning model output. We consider a supersymmetric scenario with a metastable sneutrino as a concrete example, but the methodology can be applied to a much wider class of models.
AbstractList We investigate enhancing the sensitivity of new physics searches at the LHC by machine learning in the case of background dominance and a high degree of overlap between the observables for signal and background. We use two different models, XGBoost and a deep neural network, to exploit correlations between observables and compare this approach to the traditional cut-and-count method. We consider different methods to analyze the models’ output, finding that a template fit generally performs better than a simple cut. By means of a Shapley decomposition, we gain additional insight into the relationship between event kinematics and the machine learning model output. We consider a supersymmetric scenario with a metastable sneutrino as a concrete example, but the methodology can be applied to a much wider class of models.
Abstract We investigate enhancing the sensitivity of new physics searches at the LHC by machine learning in the case of background dominance and a high degree of overlap between the observables for signal and background. We use two different models, XGBoost and a deep neural network, to exploit correlations between observables and compare this approach to the traditional cut-and-count method. We consider different methods to analyze the models’ output, finding that a template fit generally performs better than a simple cut. By means of a Shapley decomposition, we gain additional insight into the relationship between event kinematics and the machine learning model output. We consider a supersymmetric scenario with a metastable sneutrino as a concrete example, but the methodology can be applied to a much wider class of models.
Audience Academic
Author Strümke, Inga
Alvestad, Daniel
Maeland, Steffen
Kersten, Jörn
Fomin, Nikolai
Author_xml – sequence: 1
  fullname: Alvestad, Daniel
– sequence: 2
  fullname: Fomin, Nikolai
– sequence: 3
  fullname: Kersten, Jörn
– sequence: 4
  fullname: Maeland, Steffen
– sequence: 5
  fullname: Strümke, Inga
BookMark eNpVkNtKw0AQhhepYFt9BgPihRdp95Rk97IWD4WC4OE6TPYQNqTZmk3Avr2rFVHmYoafbz6YmaFJ5zuD0CXBC0I4Xpp9o5aBYJzRFFOWEpIxmsoTNCWc8TSP-eR35vwMzUJoMMaUYzFF17fm4DudqHEIieuSsIO2TYKrO4hNmQ5658M5OrXQBnPx0-fo7f7udf2Ybp8eNuvVNtVUUJkqrTWW1BRSCGukIgI403kOuLBWCALcVFJoU-mMMayyKteyoqSiJs-YwpzN0ebo1R6act-7HfSH0oMrvwPf1yX0g1OtKUEDUCoqbYqcY04hCkhuaZXZglhLouvq6Nr3_n00YSgbP_bxrFBSQQjOJC1wpBZHqoYodZ31Qw8qljY7p-KnrYv5quAik5yyL-3Nv4XIDOZjqGEMody8PP9lPwFkbnvR
ContentType Journal Article
Copyright COPYRIGHT 2023 Springer
The Author(s) 2023. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
Copyright_xml – notice: COPYRIGHT 2023 Springer
– notice: The Author(s) 2023. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
DBID ISR
7U5
8FD
8FE
8FG
ABUWG
AFKRA
ARAPS
AZQEC
BENPR
BGLVJ
CCPQU
DWQXO
H8D
HCIFZ
L7M
P5Z
P62
PHGZM
PHGZT
PIMPY
PKEHL
PQEST
PQGLB
PQQKQ
PQUKI
PRINS
DOA
DOI 10.1140/epjc/s10052-023-11532-9
DatabaseName Gale In Context: Science
Solid State and Superconductivity Abstracts
Technology Research Database
ProQuest SciTech Collection
ProQuest Technology Collection
ProQuest Central (Alumni)
ProQuest Central UK/Ireland
Advanced Technologies & Computer Science Collection
ProQuest Central Essentials
ProQuest Central
ProQuest Technology Collection
ProQuest One
ProQuest Central Korea
Aerospace Database
SciTech Premium Collection
Advanced Technologies Database with Aerospace
ProQuest advanced technologies & aerospace journals
ProQuest Advanced Technologies & Aerospace Collection
ProQuest Central Premium
ProQuest One Academic (New)
Publicly Available Content Database
ProQuest One Academic Middle East (New)
ProQuest One Academic Eastern Edition (DO NOT USE)
ProQuest One Applied & Life Sciences
ProQuest One Academic (retired)
ProQuest One Academic UKI Edition
ProQuest Central China
DOAJ Directory of Open Access Journals
DatabaseTitle Publicly Available Content Database
Technology Collection
Technology Research Database
ProQuest One Academic Middle East (New)
ProQuest Advanced Technologies & Aerospace Collection
ProQuest Central Essentials
ProQuest Central (Alumni Edition)
SciTech Premium Collection
ProQuest One Community College
ProQuest Central China
ProQuest Central
ProQuest One Applied & Life Sciences
Aerospace Database
ProQuest Central Korea
ProQuest Central (New)
Advanced Technologies Database with Aerospace
Advanced Technologies & Aerospace Collection
ProQuest One Academic Eastern Edition
ProQuest Technology Collection
ProQuest SciTech Collection
Advanced Technologies & Aerospace Database
ProQuest One Academic UKI Edition
Solid State and Superconductivity Abstracts
ProQuest One Academic
ProQuest One Academic (New)
DatabaseTitleList Publicly Available Content Database


Database_xml – sequence: 1
  dbid: DOA
  name: DOAJ Directory of Open Access Journals
  url: https://www.doaj.org/
  sourceTypes: Open Website
– sequence: 2
  dbid: PIMPY
  name: Publicly Available Content Database
  url: http://search.proquest.com/publiccontent
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Physics
EISSN 1434-6052
EndPage 22
ExternalDocumentID oai_doaj_org_article_adaa228bde764042a3c016f2b5f71ff1
A748594231
GroupedDBID -~X
.86
0R~
199
29G
2JY
30V
4.4
408
409
40D
5GY
5VS
67Z
6NX
78A
8FE
8FG
8TC
8UJ
95.
95~
AAFWJ
AAKKN
ABDBF
ABEEZ
ABMNI
ACACY
ACGFS
ACNCT
ACUHS
ACULB
ADBBV
ADMLS
AENEX
AFBBN
AFFHD
AFGXO
AFKRA
AFPKN
AFWTZ
AGWIL
AHYZX
AIBLX
ALMA_UNASSIGNED_HOLDINGS
AMKLP
ARAPS
ASPBG
AVWKF
AZFZN
B0M
BA0
BCNDV
BENPR
BGLVJ
BGNMA
C24
C6C
CCPQU
CS3
CSCUP
DL5
DU5
EAD
EAP
EAS
EBS
EMK
EPL
ER.
ESX
FEDTE
GQ8
GROUPED_DOAJ
GXS
HCIFZ
HF~
HG5
HMJXF
HVGLF
HZ~
I-F
I09
IAO
IGS
IHE
ISR
IXC
IZIGR
IZQ
I~X
KDC
KOV
LAS
M4Y
MA-
NB0
O9-
O93
OK1
P62
P9T
PHGZM
PHGZT
PIMPY
PQGLB
QOS
R89
R9I
RED
RID
RNS
ROL
RPX
RSV
S27
S3B
SDH
SOJ
SPH
T13
TN5
TSK
TSV
TUC
TUS
U2A
VC2
WK8
Z45
~8M
7U5
8FD
ABUWG
AZQEC
DWQXO
H8D
L7M
PKEHL
PQEST
PQQKQ
PQUKI
PRINS
ID FETCH-LOGICAL-d2829-cddd092e7988fe9c18a43d66a07ff881a4eb98debd5330c5b6d9b21b2e653c043
IEDL.DBID BENPR
ISSN 1434-6044
IngestDate Fri Oct 03 12:53:13 EDT 2025
Sat Oct 18 23:48:36 EDT 2025
Tue Nov 11 03:51:13 EST 2025
Thu Nov 13 16:25:44 EST 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 5
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-d2829-cddd092e7988fe9c18a43d66a07ff881a4eb98debd5330c5b6d9b21b2e653c043
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
OpenAccessLink https://www.proquest.com/docview/2811059270?pq-origsite=%requestingapplication%
PQID 2811059270
PQPubID 2034659
PageCount 22
ParticipantIDs doaj_primary_oai_doaj_org_article_adaa228bde764042a3c016f2b5f71ff1
proquest_journals_2811059270
gale_infotracacademiconefile_A748594231
gale_incontextgauss_ISR_A748594231
PublicationCentury 2000
PublicationDate 20230501
PublicationDateYYYYMMDD 2023-05-01
PublicationDate_xml – month: 05
  year: 2023
  text: 20230501
  day: 01
PublicationDecade 2020
PublicationPlace Heidelberg
PublicationPlace_xml – name: Heidelberg
PublicationTitle The European physical journal. C, Particles and fields
PublicationYear 2023
Publisher Springer
Springer Nature B.V
SpringerOpen
Publisher_xml – name: Springer
– name: Springer Nature B.V
– name: SpringerOpen
SSID ssj0002408
Score 2.4023654
Snippet We investigate enhancing the sensitivity of new physics searches at the LHC by machine learning in the case of background dominance and a high degree of...
Abstract We investigate enhancing the sensitivity of new physics searches at the LHC by machine learning in the case of background dominance and a high degree...
SourceID doaj
proquest
gale
SourceType Open Website
Aggregation Database
StartPage 379
SubjectTerms Analysis
Artificial neural networks
Decision trees
Kinematics
Large Hadron Collider
Machine learning
Neural networks
Physics
Sensitivity enhancement
SummonAdditionalLinks – databaseName: DOAJ Directory of Open Access Journals
  dbid: DOA
  link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1LS8QwEA4iCl7EJ74pongKu02bJjmqKAoi4gP2FvIURbvLtuvvd6aNoAfx4rVMYfqRZL6hX74h5ChGz4QRBVVQG2gZoWE1pfCUxW6-sQUK3bnr34jbWzkaqbtvo75QE9bbA_fADYw3hjFpfRBVCSvMFA5YSmSWR5HH2DU-wHq-mql0BqNxV1JzQQcxCJNXh7flhpxRKFIUaFDBqEo-_b-dxl2JuVwhy4kbZqd9TqtkLtRrZLHTaLpmnRz3t00yN2ub7KXOmnfz9pahAANeQlMmaHvHzQZ5urx4PL-iacoB9fgXkzrv_VCxgMZhMSiXS1MWvqrMUMQoZW7KYJX0wXoUgjpuK68syy0LFQcsymKTzNfjOmyRzBfWFq50wkDTlstonMUSzgP3ShpebJMz_F496Y0sNFpLdw8AcJ0A138Bvk0OES2N5hE1qlOezaxp9PXDvT4VpeQKCBoEnaSgOG6nxpkk9oc80W_qR-TeF-o6bZ9GM5kj72NiuPMfKe-SJZwS3-sU98h8O52FfbLgPtqXZnrQrZxPcMfGoA
  priority: 102
  providerName: Directory of Open Access Journals
Title Beyond cuts in small signal scenarios
URI https://www.proquest.com/docview/2811059270
https://doaj.org/article/adaa228bde764042a3c016f2b5f71ff1
Volume 83
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVAON
  databaseName: DOAJ Directory of Open Access Journals
  customDbUrl:
  eissn: 1434-6052
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0002408
  issn: 1434-6044
  databaseCode: DOA
  dateStart: 20140101
  isFulltext: true
  titleUrlDefault: https://www.doaj.org/
  providerName: Directory of Open Access Journals
– providerCode: PRVPQU
  databaseName: Advanced Technologies & Aerospace Database
  customDbUrl:
  eissn: 1434-6052
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0002408
  issn: 1434-6044
  databaseCode: P5Z
  dateStart: 20230101
  isFulltext: true
  titleUrlDefault: https://search.proquest.com/hightechjournals
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: ProQuest Central
  customDbUrl:
  eissn: 1434-6052
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0002408
  issn: 1434-6044
  databaseCode: BENPR
  dateStart: 20230101
  isFulltext: true
  titleUrlDefault: https://www.proquest.com/central
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Publicly Available Content Database
  customDbUrl:
  eissn: 1434-6052
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0002408
  issn: 1434-6044
  databaseCode: PIMPY
  dateStart: 20230101
  isFulltext: true
  titleUrlDefault: http://search.proquest.com/publiccontent
  providerName: ProQuest
– providerCode: PRVIAO
  databaseName: SCOAP3 Journals
  customDbUrl:
  eissn: 1434-6052
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0002408
  issn: 1434-6044
  databaseCode: ER.
  dateStart: 20140101
  isFulltext: true
  titleUrlDefault: https://scoap3.org/
  providerName: SCOAP3 (Sponsoring Consortium for Open Access Publishing in Particle Physics)
– providerCode: PRVAVX
  databaseName: Springer Nature OA Free Journals
  customDbUrl:
  eissn: 1434-6052
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0002408
  issn: 1434-6044
  databaseCode: C24
  dateStart: 19980301
  isFulltext: true
  titleUrlDefault: https://link.springer.com/search?facet-content-type=%22Journal%22
  providerName: Springer Nature
– providerCode: PRVAVX
  databaseName: SpringerLINK Contemporary 1997-Present
  customDbUrl:
  eissn: 1434-6052
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0002408
  issn: 1434-6044
  databaseCode: RSV
  dateStart: 19980103
  isFulltext: true
  titleUrlDefault: https://link.springer.com/search?facet-content-type=%22Journal%22
  providerName: Springer Nature
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3NTxUxEG_woQkXET8igmRjMJ4advuxbU8GDEQSfNmgJuil6SfB4O7j9T3_fjv7isaDXLjsoTubNu3sdKb9zW8Q2o_RE2EExSrvDZjFHLAaJjwmcaxvbLMLPbLrn4npVF5cqK4cuKUCq7y1iaOh9oODM_IDIhtwBYio389uMFSNgtvVUkLjAVoHpjI2QetHx9Pu_I8tBgKvMb-IMtzm3gvCK0cVB2H2w0EGXc0JzhsXzq4RJVgV7v7_Wehx2znZvO-An6DHxeGsDlcasoXWQv8UPRqBny49Q29XKSyVWy5SddVX6ae5vq4A1ZE_AqanHEsP6Tn6enL85cNHXEonYA9Xo9h572tFArCRxaBcIw2jvm1NLWKUsjEsWCV9sB7QpY7b1itLGktCy6mrGX2BJv3Qh5eo8tRa6pgTJkeCjYzGWfALeOBeScPpNjqCCdOzFTuGBr7qsWGYX-qi_tp4YwiR1gfRsmwnTO6kaSOxPIomxmYbvYHp1sBI0QPk5dIsU9Knn8_1oWCSq-z1ZaF3RSgOi7lxpmQQ5HECidU_kru3a6LLP5n03wV5dffrHbQBReVXsMZdNFnMl-E1euh-La7SfK-o2N4Yvednx7_ntu70U_ftN1ME2sI
linkProvider ProQuest
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Lb9QwEB6VLQgu5S1KC0SIipPVxHFi51Ch8qi66na1giKVk-tntagkS7wL4k_1N-LJZkEc4NYD18RJnMx4HvE33wC88N5SrnhOqugbCPMxYVWMW0J9199YxxC6Y9cf8fFYnJ5WkzW4XNXCIKxyZRM7Q20bg__Id6nIMBSgPH01-0qwaxTurq5aaCzV4sj9-B5TtrA3fBvlu0PpwbuTN4ek7ypALO4aEmOtTSvqkKjLu8pkQrHclqVKufdCZIo5XQnrtEXgpSl0aStNM01dWeQmZXm87zVYZ1HZxQDWJ8Pjyadfth8Jw7p6ppyRMr5tjyiLWcyum302WLGXFpRER0liKJZTUvW9Av7mETo3d3D7f_tAd2CjD6iT_eUKuAtrrr4HNzpgqwn3YWdZopOYxTwk0zoJX9TFRYKolXgRMlmpdtqEB_DxSub4EAZ1U7tHkNhc69www1XMdDPhldEY9xSusJVQRb4Jr1FAcrZk_5DIx90daNpz2S9vqaxSlAptHS9ZtIMqPiQrPdWF55n32SY8R_FKZNyoEdJzrhYhyOGH93KfM1FUMaqNg172g3wzb5VRfYVEnCeSdP0xcnulA7K3OUH-VoDH_z79DG4enhyP5Gg4PtqCWxS1sYNwbsNg3i7cE7huvs2noX3aq3cCZ1etMD8BgH81JQ
linkToPdf http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Lb9QwELZKeYgLb0ShQISoOFmbOA_bB4QKZcWq1WrFQ6q4uH5Wi0qyxLsg_hq_jpmsF8QBbj1wTZzEyXyeRzzzDSFPQ3CMa15SCbaBVgECVl1xR1kY-hsbcKEHdv0jPp2K42M52yI_NrUwmFa50YmDonadxX_kIyYKdAUYz0chpUXMDsYvFl8odpDCndZNO401RA79928QvsXnkwOQ9R5j49fvX72hqcMAdbiDSK1zLpfMI2lX8NIWQlelaxqd8xCEKHTljRTOG4dJmLY2jZOGFYb5pi5tXpVw3wvkIocYE1fXrP74ywogddhQ2VRWtIH3TrllEM-M_OKTxdq9vGYUTCYFp6xkVKauAX-zDYPBG1__nz_VDXItudnZ_npd3CRbvr1FLg_prjbeJnvrwp3MrpYxm7dZ_KzPzjLMZYGLkN9K9_Mu3iEfzmWOd8l227X-HslcaUxpK8s1xL-FCNoa9IZqXzspdF3ukJcoLLVYc4IoZOkeDnT9qUqLXmmnNWPCOM-bCrSjhocUTWCmDrwIodghT1DUCnk4WhTTqV7FqCbv3qp9Xolagq8Lg56lQaFb9trqVDcB80Tqrj9G7m7woJImiuo3GO7_-_RjcgVQoo4m08MH5CpDYA55nbtke9mv_ENyyX5dzmP_aMB5Rk7OGy0_AUkbPIg
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Beyond+cuts+in+small+signal+scenarios&rft.jtitle=The+European+physical+journal.+C%2C+Particles+and+fields&rft.au=Alvestad%2C+Daniel&rft.au=Fomin%2C+Nikolai&rft.au=Kersten%2C+J%C3%B6rn&rft.au=Maeland%2C+Steffen&rft.date=2023-05-01&rft.pub=Springer&rft.issn=1434-6044&rft.volume=83&rft.issue=5&rft_id=info:doi/10.1140%2Fepjc%2Fs10052-023-11532-9&rft.externalDBID=ISR&rft.externalDocID=A748594231
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1434-6044&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1434-6044&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1434-6044&client=summon