Autoencoders for unsupervised anomaly detection in high energy physics

A bstract Autoencoders are widely used in machine learning applications, in particular for anomaly detection. Hence, they have been introduced in high energy physics as a promising tool for model-independent new physics searches. We scrutinize the usage of autoencoders for unsupervised anomaly detec...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	The journal of high energy physics Jg. 2021; H. 6; S. 1 - 32
Hauptverfasser:	Finke, Thorben, Krämer, Michael, Morandini, Alessandro, Mück, Alexander, Oleksiyuk, Ivan
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	Berlin/Heidelberg Springer Berlin Heidelberg 01.06.2021 Springer Nature B.V SpringerOpen
Schlagworte:	Anomalies Classical and Quantum Gravitation Elementary Particles High energy physics Jets Machine learning Marking Particle physics Physics Physics and Astronomy QCD Phenomenology Quantum chromodynamics Quantum Field Theories Quantum Field Theory Quantum Physics Regular Article - Theoretical Physics Relativity Theory String Theory Jets QCD Phenomenology
ISSN:	1029-8479, 1029-8479
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Abstract	A bstract Autoencoders are widely used in machine learning applications, in particular for anomaly detection. Hence, they have been introduced in high energy physics as a promising tool for model-independent new physics searches. We scrutinize the usage of autoencoders for unsupervised anomaly detection based on reconstruction loss to show their capabilities, but also their limitations. As a particle physics benchmark scenario, we study the tagging of top jet images in a background of QCD jet images. Although we reproduce the positive results from the literature, we show that the standard autoencoder setup cannot be considered as a model-independent anomaly tagger by inverting the task: due to the sparsity and the specific structure of the jet images, the autoencoder fails to tag QCD jets if it is trained on top jets even in a semi-supervised setup. Since the same autoencoder architecture can be a good tagger for a specific example of an anomaly and a bad tagger for a different example, we suggest improved performance measures for the task of model-independent anomaly detection. We also improve the capability of the autoencoder to learn non-trivial features of the jet images, such that it is able to achieve both top jet tagging and the inverse task of QCD jet tagging with the same setup. However, we want to stress that a truly model-independent and powerful autoencoder-based unsupervised jet tagger still needs to be developed.
AbstractList	Autoencoders are widely used in machine learning applications, in particular for anomaly detection. Hence, they have been introduced in high energy physics as a promising tool for model-independent new physics searches. We scrutinize the usage of autoencoders for unsupervised anomaly detection based on reconstruction loss to show their capabilities, but also their limitations. As a particle physics benchmark scenario, we study the tagging of top jet images in a background of QCD jet images. Although we reproduce the positive results from the literature, we show that the standard autoencoder setup cannot be considered as a model-independent anomaly tagger by inverting the task: due to the sparsity and the specific structure of the jet images, the autoencoder fails to tag QCD jets if it is trained on top jets even in a semi-supervised setup. Since the same autoencoder architecture can be a good tagger for a specific example of an anomaly and a bad tagger for a different example, we suggest improved performance measures for the task of model-independent anomaly detection. We also improve the capability of the autoencoder to learn non-trivial features of the jet images, such that it is able to achieve both top jet tagging and the inverse task of QCD jet tagging with the same setup. However, we want to stress that a truly model-independent and powerful autoencoder-based unsupervised jet tagger still needs to be developed. Abstract Autoencoders are widely used in machine learning applications, in particular for anomaly detection. Hence, they have been introduced in high energy physics as a promising tool for model-independent new physics searches. We scrutinize the usage of autoencoders for unsupervised anomaly detection based on reconstruction loss to show their capabilities, but also their limitations. As a particle physics benchmark scenario, we study the tagging of top jet images in a background of QCD jet images. Although we reproduce the positive results from the literature, we show that the standard autoencoder setup cannot be considered as a model-independent anomaly tagger by inverting the task: due to the sparsity and the specific structure of the jet images, the autoencoder fails to tag QCD jets if it is trained on top jets even in a semi-supervised setup. Since the same autoencoder architecture can be a good tagger for a specific example of an anomaly and a bad tagger for a different example, we suggest improved performance measures for the task of model-independent anomaly detection. We also improve the capability of the autoencoder to learn non-trivial features of the jet images, such that it is able to achieve both top jet tagging and the inverse task of QCD jet tagging with the same setup. However, we want to stress that a truly model-independent and powerful autoencoder-based unsupervised jet tagger still needs to be developed. A bstract Autoencoders are widely used in machine learning applications, in particular for anomaly detection. Hence, they have been introduced in high energy physics as a promising tool for model-independent new physics searches. We scrutinize the usage of autoencoders for unsupervised anomaly detection based on reconstruction loss to show their capabilities, but also their limitations. As a particle physics benchmark scenario, we study the tagging of top jet images in a background of QCD jet images. Although we reproduce the positive results from the literature, we show that the standard autoencoder setup cannot be considered as a model-independent anomaly tagger by inverting the task: due to the sparsity and the specific structure of the jet images, the autoencoder fails to tag QCD jets if it is trained on top jets even in a semi-supervised setup. Since the same autoencoder architecture can be a good tagger for a specific example of an anomaly and a bad tagger for a different example, we suggest improved performance measures for the task of model-independent anomaly detection. We also improve the capability of the autoencoder to learn non-trivial features of the jet images, such that it is able to achieve both top jet tagging and the inverse task of QCD jet tagging with the same setup. However, we want to stress that a truly model-independent and powerful autoencoder-based unsupervised jet tagger still needs to be developed.
ArticleNumber	161
Author	Morandini, Alessandro Oleksiyuk, Ivan Mück, Alexander Finke, Thorben Krämer, Michael
Author_xml	– sequence: 1 givenname: Thorben surname: Finke fullname: Finke, Thorben organization: Institute for Theoretical Particle Physics and Cosmology (TTK), RWTH Aachen University – sequence: 2 givenname: Michael surname: Krämer fullname: Krämer, Michael organization: Institute for Theoretical Particle Physics and Cosmology (TTK), RWTH Aachen University – sequence: 3 givenname: Alessandro orcidid: 0000-0003-2301-7553 surname: Morandini fullname: Morandini, Alessandro email: morandini@physik.rwth-achen.de organization: Institute for Theoretical Particle Physics and Cosmology (TTK), RWTH Aachen University – sequence: 4 givenname: Alexander surname: Mück fullname: Mück, Alexander organization: Institute for Theoretical Particle Physics and Cosmology (TTK), RWTH Aachen University – sequence: 5 givenname: Ivan surname: Oleksiyuk fullname: Oleksiyuk, Ivan organization: Institute for Theoretical Particle Physics and Cosmology (TTK), RWTH Aachen University
BookMark	eNp9kE1rGzEQhkVJoPk697rQS3twopFWa-kYQpykBJpDchZTaWTLOJIr7Rb877POhrQU2tMMwzzvDM8xO0g5EWOfgJ8D5_OLb7fXD7z7IriAr9DBB3YEXJiZbufm4I_-Izuudc05KDD8iC0uhz5TctlTqU3IpRlSHbZUfsVKvsGUn3Gzazz15PqYUxNTs4rLVUOJynLXbFe7Gl09ZYcBN5XO3uoJe1pcP17dzu6_39xdXd7PXKtlPzNSONdKJEUdSuyEBJwb6nTQwnngIE1AAnQBlFfBayPAdFKi6rgWGuQJu5tyfca13Zb4jGVnM0b7OshlabH00W3I_kBtvA6tUU60zoHWzivk6KUm78J8zPo8ZW1L_jlQ7e06DyWN71uhWqW5AejGrYtpy5Vca6HwfhW43Yu3k3i7F29H8SOh_iJc7HEvry8YN__h-MTV8UJaUvn9z7-QF28fmCU
CitedBy_id	crossref_primary_10_1007_s11633_025_1554_4 crossref_primary_10_1007_s42417_025_02074_3 crossref_primary_10_1007_JHEP10_2022_085 crossref_primary_10_3390_math10060993 crossref_primary_10_1007_JHEP04_2024_059 crossref_primary_10_1016_j_eswa_2024_124108 crossref_primary_10_1007_JHEP07_2025_177 crossref_primary_10_1109_TNNLS_2024_3472456 crossref_primary_10_1007_JHEP06_2024_163 crossref_primary_10_1016_j_chemer_2024_126197 crossref_primary_10_1051_0004_6361_202347948 crossref_primary_10_1007_s00521_023_08507_y crossref_primary_10_1007_JHEP03_2022_066 crossref_primary_10_3390_s24061835 crossref_primary_10_1007_JHEP10_2022_152 crossref_primary_10_1016_j_oregeorev_2025_106705 crossref_primary_10_1007_JHEP04_2022_156 crossref_primary_10_1007_JHEP08_2021_080 crossref_primary_10_1007_JHEP01_2023_061 crossref_primary_10_1007_JHEP04_2024_109 crossref_primary_10_1111_ijfs_16283 crossref_primary_10_1140_epjc_s10052_023_12169_4 crossref_primary_10_1007_JHEP02_2022_074 crossref_primary_10_1016_j_tifs_2024_104344 crossref_primary_10_1103_PhysRevD_105_055006 crossref_primary_10_1007_JHEP11_2023_009 crossref_primary_10_3390_s21196679 crossref_primary_10_1007_s42979_024_02681_z crossref_primary_10_1016_j_jafrearsci_2025_105854 crossref_primary_10_1080_10408347_2025_2505081 crossref_primary_10_1080_13682199_2023_2202577 crossref_primary_10_1140_epjs_s11734_024_01256_6 crossref_primary_10_1140_epjc_s10052_025_14694_w crossref_primary_10_1038_s41467_024_47704_8 crossref_primary_10_1016_j_procs_2025_04_108 crossref_primary_10_1007_JHEP07_2023_108 crossref_primary_10_3389_fdata_2022_803685 crossref_primary_10_3390_s23229281 crossref_primary_10_1007_JHEP12_2021_129 crossref_primary_10_1109_TNNLS_2024_3439404 crossref_primary_10_1080_00207233_2024_2313349 crossref_primary_10_1103_PhysRevD_111_014028 crossref_primary_10_1109_SR_2025_3603142 crossref_primary_10_1109_JSTARS_2025_3568715 crossref_primary_10_1088_2632_2153_ad652b crossref_primary_10_1109_ACCESS_2022_3160170 crossref_primary_10_1134_S1063778822060023 crossref_primary_10_1007_s10661_024_12848_z crossref_primary_10_1140_epjc_s10052_022_10830_y crossref_primary_10_1016_j_jmapro_2023_05_100 crossref_primary_10_1140_epjs_s11734_024_01235_x
Cites_doi	10.1145/3439950 10.1007/JHEP10(2019)047 10.1088/1126-6708/2008/04/063 10.21468/SciPostPhys.6.3.030 10.1103/PhysRevD.98.011502 10.21468/SciPostPhys.10.2.046 10.1088/1748-0221/14/08/P08020 10.1103/PhysRevD.101.076015 10.5281/zenodo.2603256 10.1007/s10851-014-0506-3 10.1007/JHEP05(2019)036 10.1007/JHEP07(2015)086 10.1007/JHEP10(2017)174 10.1140/epjc/s10052-012-1896-2 10.1016/j.physrep.2019.11.001 10.1007/JHEP02(2018)034 10.1007/JHEP10(2018)121 10.1007/JHEP02(2014)057 10.1007/JHEP05(2017)145 10.1109/JPROC.2021.3052449 10.1142/S0217751X19300199 10.21468/SciPostPhys.5.3.028 10.1088/1742-6596/1085/2/022008 10.1007/JHEP04(2021)296 10.1146/annurev-nucl-101917-021019 10.1109/TPAMI.2013.50 10.1023/A:1026543900054 10.1103/PhysRevD.101.075021 10.3938/jkps.75.652 10.1007/JHEP10(2020)206 10.1016/j.cpc.2015.01.024 10.1140/epjc/s10052-020-08807-w 10.1007/JHEP04(2021)280 10.1007/JHEP01(2021)153 10.1016/0893-6080(89)90014-2 10.1007/JHEP05(2017)006 10.21468/SciPostPhys.7.6.075
ContentType	Journal Article
Copyright	The Author(s) 2021 The Author(s) 2021. This work is published under CC-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: The Author(s) 2021 – notice: The Author(s) 2021. This work is published under CC-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	C6C AAYXX CITATION 8FE 8FG ABUWG AFKRA ARAPS AZQEC BENPR BGLVJ CCPQU DWQXO HCIFZ P5Z P62 PHGZM PHGZT PIMPY PKEHL PQEST PQGLB PQQKQ PQUKI PRINS DOA
DOI	10.1007/JHEP06(2021)161
DatabaseName	SpringerOpen Free (Free internet resource, activated by CARLI) CrossRef ProQuest SciTech Collection ProQuest Technology Collection ProQuest Central (Alumni) ProQuest Central UK/Ireland Advanced Technologies & Computer Science Collection ProQuest Central Essentials ProQuest Central Technology Collection ProQuest One Community College ProQuest Central Korea SciTech Premium Collection Advanced Technologies & Aerospace Database 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	CrossRef Publicly Available Content Database Advanced Technologies & Aerospace Collection Technology Collection ProQuest One Academic Middle East (New) ProQuest Advanced Technologies & Aerospace Collection ProQuest Central Essentials ProQuest One Academic Eastern Edition ProQuest Central (Alumni Edition) SciTech Premium Collection ProQuest One Community College ProQuest Technology Collection ProQuest SciTech Collection ProQuest Central China ProQuest Central Advanced Technologies & Aerospace Database ProQuest One Applied & Life Sciences ProQuest One Academic UKI Edition ProQuest Central Korea ProQuest Central (New) ProQuest One Academic ProQuest One Academic (New)
DatabaseTitleList	Publicly Available Content Database CrossRef
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	1029-8479
EndPage	32
ExternalDocumentID	oai_doaj_org_article_ba89d8f495c24cc188cd5a0ad38edcf7 10_1007_JHEP06_2021_161
GroupedDBID	-5F -5G -A0 -BR 0R~ 0VY 199 1N0 30V 4.4 408 40D 5GY 5VS 8FE 8FG 8TC 8UJ 95. AAFWJ AAKKN ABEEZ ACACY ACGFS ACHIP ACREN ACULB ADBBV ADINQ AEGXH AENEX AFGXO AFKRA AFPKN AFWTZ AHBYD AHYZX AIBLX ALMA_UNASSIGNED_HOLDINGS AMKLP AMTXH AOAED ARAPS ASPBG ATQHT AVWKF AZFZN BCNDV BENPR BGLVJ C24 C6C CCPQU CS3 CSCUP DU5 EBS ER. FEDTE GQ6 GROUPED_DOAJ HCIFZ HF~ HLICF HMJXF HVGLF HZ~ IHE KOV LAP M~E N5L N9A NB0 O93 OK1 P62 P9T PIMPY PROAC R9I RO9 RSV S27 S3B SOJ SPH T13 TUS U2A VC2 VSI WK8 XPP Z45 ZMT 02O 1JI 1WK 2VQ 5ZI AAGCD AAGCF AAIAL AAJIO AALHV AARHV AATNI AAYXX ABFSG ACAFW ACARI ACBXY ACSTC ADKPE ADRFC AEFHF AEINN AEJGL AERVB AETNG AEZWR AFFHD AFHIU AFLOW AGJBK AGQPQ AHSBF AHSEE AHWEU AIXLP AIYBF AKPSB AMVHM ARNYC BAPOH BBWZM BGNMA CAG CITATION CJUJL COF CRLBU EDWGO EJD EMSAF EPQRW EQZZN H13 IJHAN IOP IZVLO JCGBZ KOT M45 M4Y NT- NT. NU0 O9- PHGZM PHGZT PJBAE PQGLB Q02 R4D RIN RKQ RNS ROL RPA S1Z S3P SY9 T37 ABUWG AZQEC DWQXO PKEHL PQEST PQQKQ PQUKI PRINS
ID	FETCH-LOGICAL-c483t-932cc43ae5e6a3a6231a79e68f82cd10139fae1acf15d5fd89219633a56082813
IEDL.DBID	DOA
ISICitedReferencesCount	78
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000669612300001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1029-8479
IngestDate	Fri Oct 03 12:52:33 EDT 2025 Sat Oct 18 22:48:58 EDT 2025 Tue Nov 18 20:05:36 EST 2025 Sat Nov 29 02:12:07 EST 2025 Fri Feb 21 02:47:58 EST 2025
IsDoiOpenAccess	true
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Issue	6
Keywords	Jets QCD Phenomenology
Language	English
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c483t-932cc43ae5e6a3a6231a79e68f82cd10139fae1acf15d5fd89219633a56082813
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0003-2301-7553
OpenAccessLink	https://doaj.org/article/ba89d8f495c24cc188cd5a0ad38edcf7
PQID	2545809116
PQPubID	2034718
PageCount	32
ParticipantIDs	doaj_primary_oai_doaj_org_article_ba89d8f495c24cc188cd5a0ad38edcf7 proquest_journals_2545809116 crossref_primary_10_1007_JHEP06_2021_161 crossref_citationtrail_10_1007_JHEP06_2021_161 springer_journals_10_1007_JHEP06_2021_161
PublicationCentury	2000
PublicationDate	2021-06-01
PublicationDateYYYYMMDD	2021-06-01
PublicationDate_xml	– month: 06 year: 2021 text: 2021-06-01 day: 01
PublicationDecade	2020
PublicationPlace	Berlin/Heidelberg
PublicationPlace_xml	– name: Berlin/Heidelberg – name: Heidelberg
PublicationTitle	The journal of high energy physics
PublicationTitleAbbrev	J. High Energ. Phys
PublicationYear	2021
Publisher	Springer Berlin Heidelberg Springer Nature B.V SpringerOpen
Publisher_xml	– name: Springer Berlin Heidelberg – name: Springer Nature B.V – name: SpringerOpen
References	LarkoskiAJMoultINachmanBJet Substructure at the Large Hadron Collider: A Review of Recent Advances in Theory and Machine LearningPhys. Rept.2020841110.1016/j.physrep.2019.11.0012020PhR...841....1L[arXiv:1709.04464] [INSPIRE] CacciariMSalamGPSoyezGThe anti-ktjet clustering algorithmJHEP20080406310.1088/1126-6708/2008/04/0632008JHEP...04..063C[arXiv:0802.1189] [INSPIRE] Y. Gershtein, D. Jaroslawski, K. Nasha, D. Shih and M. Tran, Anomaly detection with convolutional autoencoders and latent space analysis, in Anomaly Detection Mini-Workshop — LHC Summer Olympics, (2020) and publication in preparation [https://indico.desy.de/event/25341/contributions/56829/]. HajerJLiY-YLiuTWangHNovelty Detection Meets Collider PhysicsPhys. Rev. D202010107601510.1103/PhysRevD.101.0760152020PhRvD.101g6015H[arXiv:1807.10261] [INSPIRE] BatsonJHaafCGKahnYRobertsDATopological Obstructions to AutoencodingJHEP202104280427617010.1007/JHEP04(2021)2802021JHEP...04..280B[arXiv:2102.08380] [INSPIRE] AlbertssonKMachine Learning in High Energy Physics Community White PaperJ. Phys. Conf. Ser.2018108502200810.1088/1742-6596/1085/2/022008[arXiv:1807.02876] [INSPIRE] Crispim RomãoMCastroNFPedroRFinding New Physics without learning about it: Anomaly Detection as a tool for Searches at CollidersEur. Phys. J. C2021812710.1140/epjc/s10052-020-08807-w2021EPJC...81...27C[arXiv:2006.05432] [INSPIRE] ButterAKasieczkaGPlehnTRussellMDeep-learned Top Tagging with a Lorentz LayerSciPost Phys.2018502810.21468/SciPostPhys.5.3.0282018ScPP....5...28B[arXiv:1707.08966] [INSPIRE] DELPHES 3 collaboration, DELPHES 3, A modular framework for fast simulation of a generic collider experiment, JHEP02 (2014) 057 [arXiv:1307.6346] [INSPIRE]. BengioYCourvilleAVincentPRepresentation learning: A review and new perspectivesIEEE Trans. Pattern Anal. Machine Intell.201335179810.1109/TPAMI.2013.50[arXiv:1206.5538] B. Nachman, Anomaly Detection for Physics Analysis and Less than Supervised Learning, arXiv:2010.14554 [INSPIRE]. ATLAS collaboration, Observation of a new particle in the search for the Standard Model Higgs boson with the ATLAS detector at the LHC, Phys. Lett. B716 (2012) 1 [arXiv:1207.7214] [INSPIRE]. BaldiPHornikKNeural networks and principal component analysis: Learning from examples without local minimaNeural Networks198925310.1016/0893-6080(89)90014-2 OleksiyukIUnsupervised learning for tagging anomalous jets at the LHC2021Bachelor ThesisRWTH Aachen University BlanceASpannowskyMWaitePAdversarially-trained autoencoders for robust unsupervised new physics searchesJHEP20191004710.1007/JHEP10(2019)0472019JHEP...10..047B[arXiv:1905.10384] [INSPIRE] FarinaMNakaiYShihDSearching for New Physics with Deep AutoencodersPhys. Rev. D202010107502110.1103/PhysRevD.101.0750212020PhRvD.101g5021F[arXiv:1808.08992] [INSPIRE] GuestDCranmerKWhitesonDDeep Learning and its Application to LHC PhysicsAnn. Rev. Nucl. Part. Sci.20186816110.1146/annurev-nucl-101917-0210192018ARNPS..68..161G[arXiv:1806.11484] [INSPIRE] PangGShenCCaoLHengelAVDDeep Learning for Anomaly DetectionACM Computing Surveys202154110.1145/3439950[arXiv:2007.02500] F. Chollet et al., Keras, https://github.com/fchollet/keras (2015). FinkeTDeep Learning for New Physics Searches at the LHC2020Master ThesisRWTH Aachen University R. T. Schirrmeister, Y. Zhou, T. Ball and D. Zhang, Understanding Anomaly Detection with Deep Invertible Networks through Hierarchies of Distributions and Features, arXiv:2006.10848. AlmeidaLGBackovićMClicheMLeeSJPerelsteinMPlaying Tag with ANN: Boosted Top Identification with Pattern RecognitionJHEP20150708610.1007/JHEP07(2015)0862015JHEP...07..086A[arXiv:1501.05968] [INSPIRE] MacalusoSShihDPulling Out All the Tops with Computer Vision and Deep LearningJHEP20181012110.1007/JHEP10(2018)1212018JHEP...10..121M[arXiv:1803.00107] [INSPIRE] DeryLMNachmanBRubboFSchwartzmanAWeakly Supervised Classification in High Energy PhysicsJHEP20170514510.1007/JHEP05(2017)1452017JHEP...05..145D[arXiv:1702.00414] [INSPIRE] B. Bortolato, B. M. Dillon, J. F. Kamenik and A. Smolkovič, Bump Hunting in Latent Space, arXiv:2103.06595 [INSPIRE]. KomiskePTMetodievEMNachmanBSchwartzMDLearning to classify from impure samples with high-dimensional dataPhys. Rev. D20189801150210.1103/PhysRevD.98.0115022018PhRvD..98a1502K[arXiv:1801.10158] [INSPIRE] CacciariMSalamGPSoyezGFastJet User ManualEur. Phys. J. C201272189610.1140/epjc/s10052-012-1896-22012EPJC...72.1896C[arXiv:1111.6097] [INSPIRE] P. Kirichenko, P. Izmailov and A. G. Wilson, Why Normalizing Flows Fail to Detect Out-of-Distribution Data, arXiv:2006.08545. B. M. Dillon, Learning the latent structure of collider events, in Anomaly Detection Mini-Workshop — LHC Summer Olympics, (2020) [https://indico.desy.de/event/25341/contributions/56828/]. T. Sjöstrand et al., An introduction to PYTHIA 8.2, Comput. Phys. Commun.191 (2015) 159 [arXiv:1410.3012] [INSPIRE]. B. Zong et al., Deep Autoencoding Gaussian Mixture Model for Unsupervised Anomaly Detection, in International Conference on Learning Representations, Vancouver Convention Center, Vancouver, BC, Canada, April 30 – May 3, 2018 [https://openreview.net/forum?id=BJJLHbb0-]. A. Tong, G. Wolf and S. Krishnaswamy, Fixing Bias in Reconstruction-based Anomaly Detection with Lipschitz Discriminators, arXiv:1905.10710. BonneelNRabinJPeyréGPfisterHSliced and Radon Wasserstein Barycenters of MeasuresJ. Math. Imag. Vis.20155122330048210.1007/s10851-014-0506-3 T. Cheng, J.-F. Arguin, J. Leissner-Martin, J. Pilette and T. Golling, Variational Autoencoders for Anomalous Jet Tagging, arXiv:2007.01850 [INSPIRE]. HeimelTKasieczkaGPlehnTThompsonJMQCD or What?SciPost Phys.2019603010.21468/SciPostPhys.6.3.0302019ScPP....6...30H[arXiv:1808.08979] [INSPIRE] G. Kasieczka, T. Plehn, J. Thompson and M. Russel, Top Quark Tagging Reference Dataset, https://doi.org/10.5281/zenodo.2603256 (2019). LeeJSHLeeSMLeeYParkIWatsonIJYangSQuark Gluon Jet Discrimination with Weakly Supervised LearningJ. Korean Phys. Soc.20197565210.3938/jkps.75.6522019JKPS...75..652L[arXiv:2012.02540] [INSPIRE] CerriONguyenTQPieriniMSpiropuluMVlimantJ-RVariational Autoencoders for New Physics Mining at the Large Hadron ColliderJHEP20190503610.1007/JHEP05(2019)0362019JHEP...05..036C[arXiv:1811.10276] [INSPIRE] S. Alexander et al., Decoding Dark Matter Substructure without Supervision, arXiv:2008.12731 [INSPIRE]. M. Abadi et al., TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems, https://www.tensorflow.org/ (2015). M. Feickert and B. Nachman, A Living Review of Machine Learning for Particle Physics, arXiv:2102.02770 [INSPIRE]. T. S. Roy and A. H. Vijay, A robust anomaly finder based on autoencoders, arXiv:1903.02032 [INSPIRE]. M. D. Schwartz, Modern Machine Learning and Particle Physics, arXiv:2103.12226 [INSPIRE]. R. Chalapathy and S. Chawla, Deep Learning for Anomaly Detection: A Survey, arXiv:1901.03407. BourilkovDMachine and Deep Learning Applications in Particle PhysicsInt. J. Mod. Phys. A202034193001910.1142/S0217751X193001992019IJMPA..3430019B[arXiv:1912.08245] [INSPIRE] B. M. Dillon, T. Plehn, C. Sauer and P. Sorrenson, Better Latent Spaces for Better Autoencoders, arXiv:2104.08291 [INSPIRE]. BernreutherEFinkeTKahlhoeferFKrämerMMückACasting a graph net to catch dark showersSciPost Phys.20211004610.21468/SciPostPhys.10.2.0462021ScPP...10...46B[arXiv:2006.08639] [INSPIRE] RuffLA Unifying Review of Deep and Shallow Anomaly DetectionProc. IEEE202110975610.1109/JPROC.2021.3052449[arXiv:2009.11732] J. Ren et al., Likelihood Ratios for Out-of-Distribution Detection, arXiv:1906.02845. KasieczkaGPlehnTRussellMSchellTDeep-learning Top Taggers or The End of QCD?JHEP20170500610.1007/JHEP05(2017)0062017JHEP...05..006K[arXiv:1701.08784] [INSPIRE] D. Gong et al., Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detection, [arXiv:1904.02639]. G. Kasieczka et al., The LHC Olympics 2020: A Community Challenge for Anomaly Detection in High Energy Physics, arXiv:2101.08320 [INSPIRE]. ArazJYSpannowskyMCombine and Conquer: Event Reconstruction with Bayesian Ensemble Neural NetworksJHEP20210429610.1007/JHEP04(2021)2962021JHEP...04..296A[arXiv:2102.01078] [INSPIRE] J. Serrà et al., Input complexity and out-of-distribution detection with likelihood-based generative models, arXiv:1909.11480. MetodievEMNachmanBThalerJClassification without labels: Learning from mixed samples in high energy physicsJHEP20171017410.1007/JHEP10(2017)1742017JHEP...10..174M[arXiv:1708.02949] [INSPIRE] RubnerYTomasiCGuibasLJThe Earth Mover’s Distance as a Metric for Image RetrievalInt. J. Comput. Vision2000409910.1023/A:1026543900054 E. Nalisnick, A. Matsukawa, Y. W. Teh, D. Gorur and B. Lakshminarayanan, Do Deep Generative Models Know What They Don’t Know?, arXiv:1810.09136. J. Pearkes, W. Fedorko, A. Lister and C. Gay, Jet Constituents for Deep Neural Network Based Top Quark Tagging, arXiv:1704.02124 [INSPIRE]. CMS collaboration, Observation of a New Boson at a Mass of 125 GeV with the CMS Experiment at the LHC, Phys. Lett. B716 (2012) 30 [arXiv:1207.7235] [INSPIRE]. BorisyakMKazeevNMachine Learning on data with sPlot background subtractionJINST20191410.1088/1748-0221/14/08/P080202019JInst..14P8020B[arXiv:1905.11719] [INSPIRE] D. P. Kingma and J. Ba, Adam: A Method for Stochastic Optimization, arXiv:1412.6980 [INSPIRE]. ButterAThe Machine Learning landscape of top taggersSciPost Phys.2019701410.21468/SciPostPhys.7.6.0752019ScPP....7...14K[arXiv:1902.09914] [INSPIRE] T. Cohen, M. Freytsis and B. Ostdiek, (Machine) Learning to Do More with Less, JHEP02 (2018) 034 [arXiv:1706.09451] [INSPIRE]. AmramOSuarezCMTag N’ Train: a technique to train improved classifiers on unlabeled dataJHEP20210115310.1007/JHEP01(2021)1532021JHEP...01..153A[arXiv:2002.12376] [INSPIRE] J. H. Collins, P. Martín-Ramiro, B. Nachman and D. Shih, Comparing Weak- and Unsupervised Methods for Resonant Anomaly Detection, arXiv:2104.02092 [INSPIRE]. D Bourilkov (16073_CR5) 2020; 34 O Cerri (16073_CR27) 2019; 05 LM Dery (16073_CR9) 2017; 05 16073_CR38 L Ruff (16073_CR16) 2021; 109 Y Bengio (16073_CR21) 2013; 35 16073_CR36 16073_CR37 16073_CR34 16073_CR35 16073_CR32 16073_CR33 J Hajer (16073_CR23) 2020; 101 M Cacciari (16073_CR62) 2012; 72 T Heimel (16073_CR30) 2019; 6 G Kasieczka (16073_CR40) 2017; 05 JY Araz (16073_CR44) 2021; 04 A Blance (16073_CR26) 2019; 10 M Crispim Romão (16073_CR24) 2021; 81 E Bernreuther (16073_CR65) 2021; 10 A Butter (16073_CR45) 2018; 5 16073_CR49 16073_CR47 Y Rubner (16073_CR53) 2000; 40 16073_CR48 16073_CR46 16073_CR41 S Macaluso (16073_CR42) 2018; 10 G Pang (16073_CR22) 2021; 54 EM Metodiev (16073_CR11) 2017; 10 16073_CR2 P Baldi (16073_CR20) 1989; 2 16073_CR1 16073_CR4 16073_CR3 16073_CR18 16073_CR19 16073_CR17 16073_CR58 16073_CR59 16073_CR57 M Cacciari (16073_CR63) 2008; 04 16073_CR10 I Oleksiyuk (16073_CR56) 2021 16073_CR52 16073_CR50 M Farina (16073_CR31) 2020; 101 J Batson (16073_CR51) 2021; 04 N Bonneel (16073_CR54) 2015; 51 T Finke (16073_CR55) 2020 K Albertsson (16073_CR7) 2018; 1085 16073_CR29 A Butter (16073_CR43) 2019; 7 16073_CR28 16073_CR25 O Amram (16073_CR14) 2021; 01 LG Almeida (16073_CR39) 2015; 07 16073_CR64 16073_CR61 16073_CR60 AJ Larkoski (16073_CR8) 2020; 841 PT Komiske (16073_CR12) 2018; 98 M Borisyak (16073_CR13) 2019; 14 JSH Lee (16073_CR15) 2019; 75 D Guest (16073_CR6) 2018; 68
References_xml	– reference: BengioYCourvilleAVincentPRepresentation learning: A review and new perspectivesIEEE Trans. Pattern Anal. Machine Intell.201335179810.1109/TPAMI.2013.50[arXiv:1206.5538] – reference: B. Zong et al., Deep Autoencoding Gaussian Mixture Model for Unsupervised Anomaly Detection, in International Conference on Learning Representations, Vancouver Convention Center, Vancouver, BC, Canada, April 30 – May 3, 2018 [https://openreview.net/forum?id=BJJLHbb0-]. – reference: FinkeTDeep Learning for New Physics Searches at the LHC2020Master ThesisRWTH Aachen University – reference: DELPHES 3 collaboration, DELPHES 3, A modular framework for fast simulation of a generic collider experiment, JHEP02 (2014) 057 [arXiv:1307.6346] [INSPIRE]. – reference: J. Serrà et al., Input complexity and out-of-distribution detection with likelihood-based generative models, arXiv:1909.11480. – reference: E. Nalisnick, A. Matsukawa, Y. W. Teh, D. Gorur and B. Lakshminarayanan, Do Deep Generative Models Know What They Don’t Know?, arXiv:1810.09136. – reference: M. Abadi et al., TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems, https://www.tensorflow.org/ (2015). – reference: F. Chollet et al., Keras, https://github.com/fchollet/keras (2015). – reference: BorisyakMKazeevNMachine Learning on data with sPlot background subtractionJINST20191410.1088/1748-0221/14/08/P080202019JInst..14P8020B[arXiv:1905.11719] [INSPIRE] – reference: GuestDCranmerKWhitesonDDeep Learning and its Application to LHC PhysicsAnn. Rev. Nucl. Part. Sci.20186816110.1146/annurev-nucl-101917-0210192018ARNPS..68..161G[arXiv:1806.11484] [INSPIRE] – reference: CacciariMSalamGPSoyezGThe anti-ktjet clustering algorithmJHEP20080406310.1088/1126-6708/2008/04/0632008JHEP...04..063C[arXiv:0802.1189] [INSPIRE] – reference: BaldiPHornikKNeural networks and principal component analysis: Learning from examples without local minimaNeural Networks198925310.1016/0893-6080(89)90014-2 – reference: M. Feickert and B. Nachman, A Living Review of Machine Learning for Particle Physics, arXiv:2102.02770 [INSPIRE]. – reference: T. S. Roy and A. H. Vijay, A robust anomaly finder based on autoencoders, arXiv:1903.02032 [INSPIRE]. – reference: CMS collaboration, Observation of a New Boson at a Mass of 125 GeV with the CMS Experiment at the LHC, Phys. Lett. B716 (2012) 30 [arXiv:1207.7235] [INSPIRE]. – reference: KasieczkaGPlehnTRussellMSchellTDeep-learning Top Taggers or The End of QCD?JHEP20170500610.1007/JHEP05(2017)0062017JHEP...05..006K[arXiv:1701.08784] [INSPIRE] – reference: A. Tong, G. Wolf and S. Krishnaswamy, Fixing Bias in Reconstruction-based Anomaly Detection with Lipschitz Discriminators, arXiv:1905.10710. – reference: MetodievEMNachmanBThalerJClassification without labels: Learning from mixed samples in high energy physicsJHEP20171017410.1007/JHEP10(2017)1742017JHEP...10..174M[arXiv:1708.02949] [INSPIRE] – reference: LeeJSHLeeSMLeeYParkIWatsonIJYangSQuark Gluon Jet Discrimination with Weakly Supervised LearningJ. Korean Phys. Soc.20197565210.3938/jkps.75.6522019JKPS...75..652L[arXiv:2012.02540] [INSPIRE] – reference: R. T. Schirrmeister, Y. Zhou, T. Ball and D. Zhang, Understanding Anomaly Detection with Deep Invertible Networks through Hierarchies of Distributions and Features, arXiv:2006.10848. – reference: LarkoskiAJMoultINachmanBJet Substructure at the Large Hadron Collider: A Review of Recent Advances in Theory and Machine LearningPhys. Rept.2020841110.1016/j.physrep.2019.11.0012020PhR...841....1L[arXiv:1709.04464] [INSPIRE] – reference: BernreutherEFinkeTKahlhoeferFKrämerMMückACasting a graph net to catch dark showersSciPost Phys.20211004610.21468/SciPostPhys.10.2.0462021ScPP...10...46B[arXiv:2006.08639] [INSPIRE] – reference: R. Chalapathy and S. Chawla, Deep Learning for Anomaly Detection: A Survey, arXiv:1901.03407. – reference: HajerJLiY-YLiuTWangHNovelty Detection Meets Collider PhysicsPhys. Rev. D202010107601510.1103/PhysRevD.101.0760152020PhRvD.101g6015H[arXiv:1807.10261] [INSPIRE] – reference: D. P. Kingma and J. Ba, Adam: A Method for Stochastic Optimization, arXiv:1412.6980 [INSPIRE]. – reference: Crispim RomãoMCastroNFPedroRFinding New Physics without learning about it: Anomaly Detection as a tool for Searches at CollidersEur. Phys. J. C2021812710.1140/epjc/s10052-020-08807-w2021EPJC...81...27C[arXiv:2006.05432] [INSPIRE] – reference: J. Ren et al., Likelihood Ratios for Out-of-Distribution Detection, arXiv:1906.02845. – reference: B. Nachman, Anomaly Detection for Physics Analysis and Less than Supervised Learning, arXiv:2010.14554 [INSPIRE]. – reference: G. Kasieczka, T. Plehn, J. Thompson and M. Russel, Top Quark Tagging Reference Dataset, https://doi.org/10.5281/zenodo.2603256 (2019). – reference: T. Sjöstrand et al., An introduction to PYTHIA 8.2, Comput. Phys. Commun.191 (2015) 159 [arXiv:1410.3012] [INSPIRE]. – reference: J. H. Collins, P. Martín-Ramiro, B. Nachman and D. Shih, Comparing Weak- and Unsupervised Methods for Resonant Anomaly Detection, arXiv:2104.02092 [INSPIRE]. – reference: PangGShenCCaoLHengelAVDDeep Learning for Anomaly DetectionACM Computing Surveys202154110.1145/3439950[arXiv:2007.02500] – reference: CerriONguyenTQPieriniMSpiropuluMVlimantJ-RVariational Autoencoders for New Physics Mining at the Large Hadron ColliderJHEP20190503610.1007/JHEP05(2019)0362019JHEP...05..036C[arXiv:1811.10276] [INSPIRE] – reference: AlbertssonKMachine Learning in High Energy Physics Community White PaperJ. Phys. Conf. Ser.2018108502200810.1088/1742-6596/1085/2/022008[arXiv:1807.02876] [INSPIRE] – reference: FarinaMNakaiYShihDSearching for New Physics with Deep AutoencodersPhys. Rev. D202010107502110.1103/PhysRevD.101.0750212020PhRvD.101g5021F[arXiv:1808.08992] [INSPIRE] – reference: ButterAKasieczkaGPlehnTRussellMDeep-learned Top Tagging with a Lorentz LayerSciPost Phys.2018502810.21468/SciPostPhys.5.3.0282018ScPP....5...28B[arXiv:1707.08966] [INSPIRE] – reference: AlmeidaLGBackovićMClicheMLeeSJPerelsteinMPlaying Tag with ANN: Boosted Top Identification with Pattern RecognitionJHEP20150708610.1007/JHEP07(2015)0862015JHEP...07..086A[arXiv:1501.05968] [INSPIRE] – reference: B. M. Dillon, T. Plehn, C. Sauer and P. Sorrenson, Better Latent Spaces for Better Autoencoders, arXiv:2104.08291 [INSPIRE]. – reference: RuffLA Unifying Review of Deep and Shallow Anomaly DetectionProc. IEEE202110975610.1109/JPROC.2021.3052449[arXiv:2009.11732] – reference: ATLAS collaboration, Observation of a new particle in the search for the Standard Model Higgs boson with the ATLAS detector at the LHC, Phys. Lett. B716 (2012) 1 [arXiv:1207.7214] [INSPIRE]. – reference: Y. Gershtein, D. Jaroslawski, K. Nasha, D. Shih and M. Tran, Anomaly detection with convolutional autoencoders and latent space analysis, in Anomaly Detection Mini-Workshop — LHC Summer Olympics, (2020) and publication in preparation [https://indico.desy.de/event/25341/contributions/56829/]. – reference: P. Kirichenko, P. Izmailov and A. G. Wilson, Why Normalizing Flows Fail to Detect Out-of-Distribution Data, arXiv:2006.08545. – reference: T. Cheng, J.-F. Arguin, J. Leissner-Martin, J. Pilette and T. Golling, Variational Autoencoders for Anomalous Jet Tagging, arXiv:2007.01850 [INSPIRE]. – reference: ArazJYSpannowskyMCombine and Conquer: Event Reconstruction with Bayesian Ensemble Neural NetworksJHEP20210429610.1007/JHEP04(2021)2962021JHEP...04..296A[arXiv:2102.01078] [INSPIRE] – reference: OleksiyukIUnsupervised learning for tagging anomalous jets at the LHC2021Bachelor ThesisRWTH Aachen University – reference: BonneelNRabinJPeyréGPfisterHSliced and Radon Wasserstein Barycenters of MeasuresJ. Math. Imag. Vis.20155122330048210.1007/s10851-014-0506-3 – reference: M. D. Schwartz, Modern Machine Learning and Particle Physics, arXiv:2103.12226 [INSPIRE]. – reference: AmramOSuarezCMTag N’ Train: a technique to train improved classifiers on unlabeled dataJHEP20210115310.1007/JHEP01(2021)1532021JHEP...01..153A[arXiv:2002.12376] [INSPIRE] – reference: DeryLMNachmanBRubboFSchwartzmanAWeakly Supervised Classification in High Energy PhysicsJHEP20170514510.1007/JHEP05(2017)1452017JHEP...05..145D[arXiv:1702.00414] [INSPIRE] – reference: T. Cohen, M. Freytsis and B. Ostdiek, (Machine) Learning to Do More with Less, JHEP02 (2018) 034 [arXiv:1706.09451] [INSPIRE]. – reference: B. M. Dillon, Learning the latent structure of collider events, in Anomaly Detection Mini-Workshop — LHC Summer Olympics, (2020) [https://indico.desy.de/event/25341/contributions/56828/]. – reference: BourilkovDMachine and Deep Learning Applications in Particle PhysicsInt. J. Mod. Phys. A202034193001910.1142/S0217751X193001992019IJMPA..3430019B[arXiv:1912.08245] [INSPIRE] – reference: S. Alexander et al., Decoding Dark Matter Substructure without Supervision, arXiv:2008.12731 [INSPIRE]. – reference: BatsonJHaafCGKahnYRobertsDATopological Obstructions to AutoencodingJHEP202104280427617010.1007/JHEP04(2021)2802021JHEP...04..280B[arXiv:2102.08380] [INSPIRE] – reference: D. Gong et al., Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detection, [arXiv:1904.02639]. – reference: J. Pearkes, W. Fedorko, A. Lister and C. Gay, Jet Constituents for Deep Neural Network Based Top Quark Tagging, arXiv:1704.02124 [INSPIRE]. – reference: CacciariMSalamGPSoyezGFastJet User ManualEur. Phys. J. C201272189610.1140/epjc/s10052-012-1896-22012EPJC...72.1896C[arXiv:1111.6097] [INSPIRE] – reference: KomiskePTMetodievEMNachmanBSchwartzMDLearning to classify from impure samples with high-dimensional dataPhys. Rev. D20189801150210.1103/PhysRevD.98.0115022018PhRvD..98a1502K[arXiv:1801.10158] [INSPIRE] – reference: B. Bortolato, B. M. Dillon, J. F. Kamenik and A. Smolkovič, Bump Hunting in Latent Space, arXiv:2103.06595 [INSPIRE]. – reference: RubnerYTomasiCGuibasLJThe Earth Mover’s Distance as a Metric for Image RetrievalInt. J. Comput. Vision2000409910.1023/A:1026543900054 – reference: G. Kasieczka et al., The LHC Olympics 2020: A Community Challenge for Anomaly Detection in High Energy Physics, arXiv:2101.08320 [INSPIRE]. – reference: BlanceASpannowskyMWaitePAdversarially-trained autoencoders for robust unsupervised new physics searchesJHEP20191004710.1007/JHEP10(2019)0472019JHEP...10..047B[arXiv:1905.10384] [INSPIRE] – reference: HeimelTKasieczkaGPlehnTThompsonJMQCD or What?SciPost Phys.2019603010.21468/SciPostPhys.6.3.0302019ScPP....6...30H[arXiv:1808.08979] [INSPIRE] – reference: MacalusoSShihDPulling Out All the Tops with Computer Vision and Deep LearningJHEP20181012110.1007/JHEP10(2018)1212018JHEP...10..121M[arXiv:1803.00107] [INSPIRE] – reference: ButterAThe Machine Learning landscape of top taggersSciPost Phys.2019701410.21468/SciPostPhys.7.6.0752019ScPP....7...14K[arXiv:1902.09914] [INSPIRE] – ident: 16073_CR48 – volume: 54 start-page: 1 year: 2021 ident: 16073_CR22 publication-title: ACM Computing Surveys doi: 10.1145/3439950 – volume-title: Unsupervised learning for tagging anomalous jets at the LHC year: 2021 ident: 16073_CR56 – ident: 16073_CR25 – volume: 10 start-page: 047 year: 2019 ident: 16073_CR26 publication-title: JHEP doi: 10.1007/JHEP10(2019)047 – volume: 04 start-page: 063 year: 2008 ident: 16073_CR63 publication-title: JHEP doi: 10.1088/1126-6708/2008/04/063 – volume: 6 start-page: 030 year: 2019 ident: 16073_CR30 publication-title: SciPost Phys. doi: 10.21468/SciPostPhys.6.3.030 – volume: 98 start-page: 011502 year: 2018 ident: 16073_CR12 publication-title: Phys. Rev. D doi: 10.1103/PhysRevD.98.011502 – ident: 16073_CR2 – ident: 16073_CR50 – volume: 10 start-page: 046 year: 2021 ident: 16073_CR65 publication-title: SciPost Phys. doi: 10.21468/SciPostPhys.10.2.046 – volume: 14 year: 2019 ident: 16073_CR13 publication-title: JINST doi: 10.1088/1748-0221/14/08/P08020 – ident: 16073_CR18 – volume: 101 start-page: 076015 year: 2020 ident: 16073_CR23 publication-title: Phys. Rev. D doi: 10.1103/PhysRevD.101.076015 – ident: 16073_CR35 – ident: 16073_CR46 doi: 10.5281/zenodo.2603256 – volume: 51 start-page: 22 year: 2015 ident: 16073_CR54 publication-title: J. Math. Imag. Vis. doi: 10.1007/s10851-014-0506-3 – volume: 05 start-page: 036 year: 2019 ident: 16073_CR27 publication-title: JHEP doi: 10.1007/JHEP05(2019)036 – volume: 07 start-page: 086 year: 2015 ident: 16073_CR39 publication-title: JHEP doi: 10.1007/JHEP07(2015)086 – ident: 16073_CR49 – volume: 10 start-page: 174 year: 2017 ident: 16073_CR11 publication-title: JHEP doi: 10.1007/JHEP10(2017)174 – ident: 16073_CR28 – ident: 16073_CR41 – ident: 16073_CR3 – volume: 72 start-page: 1896 year: 2012 ident: 16073_CR62 publication-title: Eur. Phys. J. C doi: 10.1140/epjc/s10052-012-1896-2 – volume: 841 start-page: 1 year: 2020 ident: 16073_CR8 publication-title: Phys. Rept. doi: 10.1016/j.physrep.2019.11.001 – ident: 16073_CR10 doi: 10.1007/JHEP02(2018)034 – ident: 16073_CR59 – ident: 16073_CR38 – volume: 10 start-page: 121 year: 2018 ident: 16073_CR42 publication-title: JHEP doi: 10.1007/JHEP10(2018)121 – ident: 16073_CR61 doi: 10.1007/JHEP02(2014)057 – ident: 16073_CR34 – ident: 16073_CR17 – volume: 05 start-page: 145 year: 2017 ident: 16073_CR9 publication-title: JHEP doi: 10.1007/JHEP05(2017)145 – volume: 109 start-page: 756 year: 2021 ident: 16073_CR16 publication-title: Proc. IEEE doi: 10.1109/JPROC.2021.3052449 – volume: 34 start-page: 1930019 year: 2020 ident: 16073_CR5 publication-title: Int. J. Mod. Phys. A doi: 10.1142/S0217751X19300199 – volume: 5 start-page: 028 year: 2018 ident: 16073_CR45 publication-title: SciPost Phys. doi: 10.21468/SciPostPhys.5.3.028 – volume: 1085 start-page: 022008 year: 2018 ident: 16073_CR7 publication-title: J. Phys. Conf. Ser. doi: 10.1088/1742-6596/1085/2/022008 – volume: 04 start-page: 296 year: 2021 ident: 16073_CR44 publication-title: JHEP doi: 10.1007/JHEP04(2021)296 – ident: 16073_CR4 – volume: 68 start-page: 161 year: 2018 ident: 16073_CR6 publication-title: Ann. Rev. Nucl. Part. Sci. doi: 10.1146/annurev-nucl-101917-021019 – volume: 35 start-page: 1798 year: 2013 ident: 16073_CR21 publication-title: IEEE Trans. Pattern Anal. Machine Intell. doi: 10.1109/TPAMI.2013.50 – volume: 40 start-page: 99 year: 2000 ident: 16073_CR53 publication-title: Int. J. Comput. Vision doi: 10.1023/A:1026543900054 – ident: 16073_CR33 – volume: 101 start-page: 075021 year: 2020 ident: 16073_CR31 publication-title: Phys. Rev. D doi: 10.1103/PhysRevD.101.075021 – volume-title: Deep Learning for New Physics Searches at the LHC year: 2020 ident: 16073_CR55 – volume: 75 start-page: 652 year: 2019 ident: 16073_CR15 publication-title: J. Korean Phys. Soc. doi: 10.3938/jkps.75.652 – ident: 16073_CR37 – ident: 16073_CR52 – ident: 16073_CR47 – ident: 16073_CR58 doi: 10.1007/JHEP10(2020)206 – ident: 16073_CR64 – ident: 16073_CR60 doi: 10.1016/j.cpc.2015.01.024 – volume: 81 start-page: 27 year: 2021 ident: 16073_CR24 publication-title: Eur. Phys. J. C doi: 10.1140/epjc/s10052-020-08807-w – ident: 16073_CR29 – volume: 04 start-page: 280 year: 2021 ident: 16073_CR51 publication-title: JHEP doi: 10.1007/JHEP04(2021)280 – volume: 01 start-page: 153 year: 2021 ident: 16073_CR14 publication-title: JHEP doi: 10.1007/JHEP01(2021)153 – volume: 2 start-page: 53 year: 1989 ident: 16073_CR20 publication-title: Neural Networks doi: 10.1016/0893-6080(89)90014-2 – volume: 05 start-page: 006 year: 2017 ident: 16073_CR40 publication-title: JHEP doi: 10.1007/JHEP05(2017)006 – ident: 16073_CR1 – ident: 16073_CR57 – ident: 16073_CR32 – volume: 7 start-page: 014 year: 2019 ident: 16073_CR43 publication-title: SciPost Phys. doi: 10.21468/SciPostPhys.7.6.075 – ident: 16073_CR19 – ident: 16073_CR36
SSID	ssj0015190
Score	2.6531794
Snippet	A bstract Autoencoders are widely used in machine learning applications, in particular for anomaly detection. Hence, they have been introduced in high energy... Autoencoders are widely used in machine learning applications, in particular for anomaly detection. Hence, they have been introduced in high energy physics as... Abstract Autoencoders are widely used in machine learning applications, in particular for anomaly detection. Hence, they have been introduced in high energy...
SourceID	doaj proquest crossref springer
SourceType	Open Website Aggregation Database Enrichment Source Index Database Publisher
StartPage	1
SubjectTerms	Anomalies Classical and Quantum Gravitation Elementary Particles High energy physics Jets Machine learning Marking Particle physics Physics Physics and Astronomy QCD Phenomenology Quantum chromodynamics Quantum Field Theories Quantum Field Theory Quantum Physics Regular Article - Theoretical Physics Relativity Theory String Theory
SummonAdditionalLinks	– databaseName: Advanced Technologies & Aerospace Database dbid: P5Z link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1NT9wwEB1RaCUuFEortnzIBw5wSFnn0z4hilitEFrtARDqJbLGDkKCZLvJVuq_74yTLAKJXrgmdmTljT3PnvEbgENpiASoNA0MFiqIjZKBxsQG2hYSyWFHodcpuL3KJhN1d6en3YFb3aVV9muiX6hthXxGfhJyhIecm0xPZ78DrhrF0dWuhMYHWGOVBC7dME1-LaMIxE6GvZzPMDu5HF9Mh-kRbfflsUzlC0_kBftfsMxXgVHvb0af3zvSTdjomKY4a01jC1Zc-QU--YxPrLdhdLZoKlax5ExmQdRVLMp6MeOlo3ZWmLJ6Mo9_hXWNT9YqxUMpWNtYOH9bULRHIvVXuBldXJ-Pg66oQoCxipqA-BpiHBmXuNREhtiPNJl2qSpUiFYyIyyMkwSdTGxSWKVDnqSRIWpEuzMZfYPVsirdDgibOOqNmSbaEruMmI1JiNCxppdGq6MB_Oh_cI6d4jgXvnjMe63kFpGcEckJkQEcLTvMWrGNt5v-ZMSWzVgl2z-o5vd5N-mICChtVUF7QAxjRKkU2sQMjY2Us1hkA9jrEcy7qVvnz_AN4Li3gefXb4zn-_8_tQvr3LLNMduD1Wa-cPvwEf80D_X8wFvtP9VT8yE priority: 102 providerName: ProQuest – databaseName: SpringerLINK dbid: C24 link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1LS8QwEB7EB3jxLa6ukoOH9VDZ9JkcVXYRkcWDircSJqksrO2y7Qr-eydpu7KKB72VdgJhJsl805n5AnDOFYEAEceewkx4oRLckxhpT-qMIznswHc8Bc_3yWgkXl7kwwrwthfGVbu3KUl3UrfNbne3g4d-3KNgnV9wG_CsRVxIW8V3YxscmsQBAZJ-y-Dzc9CS83Ec_UvA8lsu1LmY4fY_JrcDWw2eZFf1AtiFFZPvwYar68RyH4ZX86qwXJW2XpkRQGXzvJxP7QFRGs1UXrypyQfTpnIlWTkb58wyGDPjegJZ_eOjPICn4eDx5tZrrk7wMBRB5REqQwwDZSITq0ARxuEqkSYWmfBRc4v7MmU4GYhHOsq0kL7dioEiAEQxGA8OYTUvcnMETEeGRmMiCZyEJiH8oiKCbZa5S6KWQQcuW52m2PCK2-stJmnLiFwrJ7XKSUk5HegtBkxrSo3fRa-tkRZilgvbvShmr2mztcjdC6lFRpEe-iEiFwJ1pPpKB8JozJIOdFsTp80GLVPfJgwJK_G4AxetSb8-_zKf4z_InsCmfazLyrqwWs3m5hTW8b0al7Mzt2o_AaUC5po priority: 102 providerName: Springer Nature
Title	Autoencoders for unsupervised anomaly detection in high energy physics
URI	https://link.springer.com/article/10.1007/JHEP06(2021)161 https://www.proquest.com/docview/2545809116 https://doaj.org/article/ba89d8f495c24cc188cd5a0ad38edcf7
Volume	2021
WOSCitedRecordID	wos000669612300001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText	1
inHoldings	1
isFullTextHit
isPrint
journalDatabaseRights	– providerCode: PRVAON databaseName: DOAJ Directory of Open Access Journals customDbUrl: eissn: 1029-8479 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0015190 issn: 1029-8479 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: 1029-8479 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0015190 issn: 1029-8479 databaseCode: P5Z dateStart: 20100101 isFulltext: true titleUrlDefault: https://search.proquest.com/hightechjournals providerName: ProQuest – providerCode: PRVPQU databaseName: ProQuest Central customDbUrl: eissn: 1029-8479 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0015190 issn: 1029-8479 databaseCode: BENPR dateStart: 20100101 isFulltext: true titleUrlDefault: https://www.proquest.com/central providerName: ProQuest – providerCode: PRVPQU databaseName: Publicly Available Content Database customDbUrl: eissn: 1029-8479 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0015190 issn: 1029-8479 databaseCode: PIMPY dateStart: 20100101 isFulltext: true titleUrlDefault: http://search.proquest.com/publiccontent providerName: ProQuest – providerCode: PRVIAO databaseName: SCOAP3 Journals customDbUrl: eissn: 1029-8479 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0015190 issn: 1029-8479 databaseCode: ER. dateStart: 20140101 isFulltext: true titleUrlDefault: https://scoap3.org/ providerName: SCOAP3 (Sponsoring Consortium for Open Access Publishing in Particle Physics) – providerCode: PRVAVX databaseName: SpringerLINK customDbUrl: eissn: 1029-8479 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0015190 issn: 1029-8479 databaseCode: C24 dateStart: 20100101 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/eLvHCXMwrZ3Pa9swFMcfW7dBL2U_qfsj6LBDcvBq-ad0bENCNrZgxjayXYz2JEMgdUrtFPrf90m2s2YQdtnFB1sy4vss9JH19BXAe64IAkSa-gpL4cdKcF9ion2pS440YEeh8yn48Tmbz8ViIfNHR33ZnLDWHrgV7uK3ElKLkjgewxiRC4E6UYHSkTAaS7ePPMhkP5nq1g-IS4LeyCfILj7NJnmQDmmiz0c85TtjkLPq3-HLv5ZE3UgzfQlHHSKyy7Zpr-CJqV7DC5eqifUbmF5umrW1n7QpyIyYk22qenNj-3xtNFPV-lqt7pk2jcuyqtiyYtaUmBm3zY-1_zLqt_B9Ovk2nvndaQg-xiJqfAItxDhSJjGpihRhC1eZNKkoRYiaW5QrleGkOU90UmohQ9u7IkVMQ9MqHr2Dg2pdmWNgOjFUGzNJvBGbjJBEJURi1oxLopaRBx96fQrsrMLtiRWrojc5bgUtrKAFCerBcFvhpnXJ2F_0ygq-LWbtrd0NCnrRBb34V9A9OOvDVXR9ri5CuwZI-MNTD0Z9CP883tOek__RnlM4tO9rU8jO4KC53ZhzeI53zbK-HcCzq8k8_zqAp-MwHrgPla558oue5B-_5D8fAIwA68Y
linkProvider	Directory of Open Access Journals
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Lb9QwEB6VLQguPItYKOADSO0hdJ2nfUCoQFe7dLvaQ0HllFpjB1UqybLJtuqf4jcyk8dWRSq3HrgmseXEX2Y-e8bfALyRhkiAimPPYKa80CjpaYysp20mkRx24Nc6Bd8myXSqjo70bA1-d2dhOK2ys4m1obYF8h75js8RHnJuMv4w_-Vx1SiOrnYlNBpY7LuLc1qyle_Hn2l-3_r-cO_w08hrqwp4GKqg8oiwIIaBcZGLTWDI_UuTaBerTPloJVOizDhJY5eRjTKrtM8oDQxxA1qeyID6vQXrIYO9B-uz8cHs-ypuQXxo0AkIDZKdL6O92SDe8smRbstYXvF9dYmAK7z2r1Bs7eGGD_63b_MQ7rdcWuw24H8Eay5_DHfqnFYsn8Bwd1kVrNPJudqCyLlY5uVyzsaxdFaYvPhpTi-EdVWdjpaLk1ywerNw9XlI0Wz6lBvw9UZe4in08iJ3z0DYyFFrTDQRs9AlxN1MRJSVVcs0Wh304V03oSm2mupc2uM07dSgGwSkjICUENCHrVWDeSMncv2jHxkhq8dYB7y-UCx-pK1ZIaqjtFUZrXLRDxGlUmgjMzA2UM5ilvRhs0NM2hqnMr2ESx-2O8xd3r5mPM__3dVruDs6PJikk_F0_wXc41ZNRt0m9KrF0r2E23hWnZSLV-0_I-D4pqH4B4rwUB0
linkToPdf	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Lb9QwEB6V8lAv5S2WFvABpPYQdp2nfUCo0K5aWq32AKjiklpjB1UqybLJFvWv8euYcZKtilRuPXBNbCuOP898tsffALyWhkiAStPAYKGC2CgZaExsoG0hkRx2FHqdgq9H2WSijo_1dAV-93dhOKyyt4neUNsKeY98GPIJDzk3mQ6LLixiujt-P_sZcAYpPmnt02m0EDl0F79o-Va_O9ilsX4ThuO9zx_3gy7DQICxipqAyAtiHBmXuNREhqiANJl2qSpUiFYyPSqMk9QPmdiksEqHjNjIEE-gpYqMqN1bcDujNSaHE06Tb8sTDGJGo15KaJQNP-3vTUfpVkgudVum8ooX9MkCrjDcvw5lva8b3_-f_9IDWO8Ytthpp8RDWHHlI7jrI12xfgzjnUVTsXonR3ALouxiUdaLGZvM2llhyuqHObsQ1jU-SK0Up6VgTWfh_C1J0W4F1U_gy4104imsllXpnoGwiaPamGmia7HLiNGZhIgsa5lptDoawNt-cHPslNY54cdZ3mtEt2jIGQ05oWEAW8sKs1Zk5PqiHxgty2KsDu4fVPPveWdsiAApbVVBa18MY0SpFNrEjIyNlLNYZAPY7NGTdyarzi-hM4DtHn-Xr6_5nuf_buoV3CP85UcHk8MNWONKbZjdJqw284V7AXfwvDmt5y_95BFwctM4_APxoFeA
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=Autoencoders+for+unsupervised+anomaly+detection+in+high+energy+physics&rft.jtitle=The+journal+of+high+energy+physics&rft.au=Thorben+Finke&rft.au=Michael+Kr%C3%A4mer&rft.au=Alessandro+Morandini&rft.au=Alexander+M%C3%BCck&rft.date=2021-06-01&rft.pub=SpringerOpen&rft.eissn=1029-8479&rft.volume=2021&rft.issue=6&rft.spage=1&rft.epage=32&rft_id=info:doi/10.1007%2FJHEP06%282021%29161&rft.externalDBID=DOA&rft.externalDocID=oai_doaj_org_article_ba89d8f495c24cc188cd5a0ad38edcf7
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1029-8479&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1029-8479&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1029-8479&client=summon