000642844 001__ 642844
000642844 005__ 20251217123023.0
000642844 0247_ $$2doi$$a10.1088/2632-2153/ae0def
000642844 037__ $$aPUBDB-2025-05650
000642844 082__ $$a621.3
000642844 1001_ $$aDrnevich, Matthew$$b0
000642844 245__ $$aNeural quasiprobabilistic likelihood ratio estimation with negatively weighted data
000642844 260__ $$aBristol$$bIOP Publishing$$c2025
000642844 3367_ $$2DRIVER$$aarticle
000642844 3367_ $$2DataCite$$aOutput Types/Journal article
000642844 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1765970789_3472940
000642844 3367_ $$2BibTeX$$aARTICLE
000642844 3367_ $$2ORCID$$aJOURNAL_ARTICLE
000642844 3367_ $$00$$2EndNote$$aJournal Article
000642844 520__ $$aMLST-IOPscience-Header.pngPurpose-Led Publishing logo.Part of the Machine Learning Series logo.Paper • The following article is Open accessNeural quasiprobabilistic likelihood ratio estimation with negatively weighted dataMatthew Drnevich, Stephen Jiggins*, Judith Katzy and Kyle CranmerPublished 28 October 2025 • © 2025 The Author(s). Published by IOP Publishing LtdMachine Learning: Science and Technology, Volume 6, Number 4Focus on ML and the Physical SciencesCitation Matthew Drnevich et al 2025 Mach. Learn.: Sci. Technol. 6 045023DOI 10.1088/2632-2153/ae0defDownload Article PDFArticle metrics172 Total downloads11 citation on Dimensions.SubmitSubmit to this JournalShare this articleAbstractMotivated by real-world situations found in high energy particle physics, we consider a generalization of the likelihood-ratio estimation task to a quasiprobabilistic setting where probability densities can be negative, and to importance sampling where the importance weights can be negative. The presence of negative densities and negative weights, pose an array of challenges to traditional neural likelihood ratio (LR) estimation methods. We address these challenges by introducing a novel loss function. In addition, we introduce a new model architecture based on the decomposition of a LR using signed mixture models, providing a second strategy for overcoming these challenges. Finally, we demonstrate our approach on a pedagogical example and a real-world example from particle physics.
000642844 536__ $$0G:(DE-HGF)POF4-611$$a611 - Fundamental Particles and Forces (POF4-611)$$cPOF4-611$$fPOF IV$$x0
000642844 588__ $$aDataset connected to CrossRef, Journals: bib-pubdb1.desy.de
000642844 693__ $$0EXP:(DE-H253)LHC-Exp-ATLAS-20150101$$1EXP:(DE-588)4398783-7$$5EXP:(DE-H253)LHC-Exp-ATLAS-20150101$$aLHC$$eLHC: ATLAS$$x0
000642844 7001_ $$0P:(DE-H253)PIP1094134$$aJiggins, Stephen$$b1$$eCorresponding author
000642844 7001_ $$0P:(DE-H253)PIP1002273$$aKatzy, Judith$$b2$$eCorresponding author
000642844 7001_ $$0P:(DE-H253)PIP1114050$$aCranmer, Kyle$$b3$$eCorresponding author
000642844 773__ $$0PERI:(DE-600)3017004-7$$a10.1088/2632-2153/ae0def$$gVol. 6, no. 4, p. 045023 -$$n4$$p045023 -$$tMachine learning: science and technology$$v6$$x2632-2153$$y2025
000642844 8564_ $$uhttps://bib-pubdb1.desy.de/record/642844/files/Drnevich_2025_Mach._Learn.__Sci._Technol._6_045023.pdf$$yRestricted
000642844 8564_ $$uhttps://bib-pubdb1.desy.de/record/642844/files/Drnevich_2025_Mach._Learn.__Sci._Technol._6_045023.pdf?subformat=pdfa$$xpdfa$$yRestricted
000642844 9101_ $$0I:(DE-588b)2008985-5$$6P:(DE-H253)PIP1094134$$aDeutsches Elektronen-Synchrotron$$b1$$kDESY
000642844 9101_ $$0I:(DE-588b)2008985-5$$6P:(DE-H253)PIP1002273$$aDeutsches Elektronen-Synchrotron$$b2$$kDESY
000642844 9101_ $$0I:(DE-HGF)0$$6P:(DE-H253)PIP1114050$$aExternal Institute$$b3$$kExtern
000642844 9131_ $$0G:(DE-HGF)POF4-611$$1G:(DE-HGF)POF4-610$$2G:(DE-HGF)POF4-600$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$aDE-HGF$$bForschungsbereich Materie$$lMatter and the Universe$$vFundamental Particles and Forces$$x0
000642844 915__ $$0StatID:(DE-HGF)0100$$2StatID$$aJCR$$bMACH LEARN-SCI TECHN : 2022$$d2025-01-01
000642844 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS$$d2025-01-01
000642844 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline$$d2025-01-01
000642844 915__ $$0StatID:(DE-HGF)0501$$2StatID$$aDBCoverage$$bDOAJ Seal$$d2024-08-08T17:02:38Z
000642844 915__ $$0StatID:(DE-HGF)0500$$2StatID$$aDBCoverage$$bDOAJ$$d2024-08-08T17:02:38Z
000642844 915__ $$0StatID:(DE-HGF)0030$$2StatID$$aPeer Review$$bDOAJ : Anonymous peer review$$d2024-08-08T17:02:38Z
000642844 915__ $$0LIC:(DE-HGF)CCBYNV$$2V:(DE-HGF)$$aCreative Commons Attribution CC BY (No Version)$$bDOAJ$$d2024-08-08T17:02:38Z
000642844 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bClarivate Analytics Master Journal List$$d2025-01-01
000642844 915__ $$0StatID:(DE-HGF)1150$$2StatID$$aDBCoverage$$bCurrent Contents - Physical, Chemical and Earth Sciences$$d2025-01-01
000642844 915__ $$0StatID:(DE-HGF)1160$$2StatID$$aDBCoverage$$bCurrent Contents - Engineering, Computing and Technology$$d2025-01-01
000642844 915__ $$0StatID:(DE-HGF)0160$$2StatID$$aDBCoverage$$bEssential Science Indicators$$d2025-01-01
000642844 915__ $$0StatID:(DE-HGF)0113$$2StatID$$aWoS$$bScience Citation Index Expanded$$d2025-01-01
000642844 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection$$d2025-01-01
000642844 915__ $$0StatID:(DE-HGF)9905$$2StatID$$aIF >= 5$$bMACH LEARN-SCI TECHN : 2022$$d2025-01-01
000642844 915__ $$0StatID:(DE-HGF)0561$$2StatID$$aArticle Processing Charges$$d2025-01-01
000642844 915__ $$0StatID:(DE-HGF)0700$$2StatID$$aFees$$d2025-01-01
000642844 9201_ $$0I:(DE-H253)ATLAS-20120731$$kATLAS$$lLHC/ATLAS Experiment$$x0
000642844 980__ $$ajournal
000642844 980__ $$aEDITORS
000642844 980__ $$aVDBINPRINT
000642844 980__ $$aI:(DE-H253)ATLAS-20120731
000642844 980__ $$aUNRESTRICTED