000605866 001__ 605866
000605866 005__ 20240423211856.0
000605866 037__ $$aPUBDB-2024-01548
000605866 041__ $$aEnglish
000605866 1001_ $$0P:(DE-H253)PIP1088561$$aBach, Jörn$$b0$$eCorresponding author
000605866 1112_ $$aDPG Spring Meeting (German Physical Society)$$cKarlsruhe$$d2024-03-04 - 2024-03-08$$gDPG2024$$wGermany
000605866 245__ $$aDealing with negatively weighted Events in DNN-based LHC Analyses
000605866 260__ $$c2024
000605866 3367_ $$033$$2EndNote$$aConference Paper
000605866 3367_ $$2DataCite$$aOther
000605866 3367_ $$2BibTeX$$aINPROCEEDINGS
000605866 3367_ $$2DRIVER$$aconferenceObject
000605866 3367_ $$2ORCID$$aLECTURE_SPEECH
000605866 3367_ $$0PUB:(DE-HGF)6$$2PUB:(DE-HGF)$$aConference Presentation$$bconf$$mconf$$s1713871349_4112474
000605866 520__ $$aThe recent decade has seen a growth of machine learning algorithms across all disciplines. In LHC physics, a multitude of applications have been tested and - in particular Deep Neural Networks (DNNs) - have been proven to be very effective in various usecases, for example in particle tagging or for separating signal from background in analyses. Since training data is primarily generated through Monte-Carlo (MC) simulation, specific challenges can emerge during DNN training due to partly negatively weighted samples. MC simulations produce negative event weights in the presence of destructive interference in the process or in the case of next-to-leading order simulations with an additive matching scheme. The negatively weighted training data impair the DNN convergence. Therefore, the current state of the art is to use reweighting methods that lead to consistently positive weights. However this alters the input distribution. We propose an alternative technique that is interpretable, computationally efficient and does not affect the input distribution. Furthermore, we show the method employed on a hypothetical search for a beyond the standard model heavy Higgs boson and discuss implications of negative weights throughout DNN based analyses.
000605866 536__ $$0G:(DE-HGF)POF4-611$$a611 - Fundamental Particles and Forces (POF4-611)$$cPOF4-611$$fPOF IV$$x0
000605866 693__ $$0EXP:(DE-H253)LHC-Exp-CMS-20150101$$1EXP:(DE-588)4398783-7$$5EXP:(DE-H253)LHC-Exp-CMS-20150101$$aLHC$$eLHC: CMS$$x0
000605866 7001_ $$0P:(DE-H253)PIP1024695$$aSchwanenberger, Christian$$b1
000605866 7001_ $$0P:(DE-H253)PIP1097777$$aStelldinger, Peer$$b2
000605866 7001_ $$0P:(DE-H253)PIP1015292$$aGrohsjean, Alexander$$b3
000605866 7870_ $$0PUBDB-2024-01175$$aGallo-Voss, Elisabetta et.al.$$d2024$$iIsMemberOf$$r$$tSearch for singly-produced vector-like top quark decaying to top and Higgs inopposite sign di-lepton final state in proton-proton collision at $\sqrt{s}$ = 13TeV 
000605866 8564_ $$uhttps://www.dpg-verhandlungen.de/year/2024/conference/karlsruhe/part/t/session/68/contribution/7
000605866 8564_ $$uhttps://bib-pubdb1.desy.de/record/605866/files/bach_dpg_negativeweights.pdf$$yRestricted
000605866 8564_ $$uhttps://bib-pubdb1.desy.de/record/605866/files/bach_dpg_negativeweights.pdf?subformat=pdfa$$xpdfa$$yRestricted
000605866 909CO $$ooai:bib-pubdb1.desy.de:605866$$pVDB
000605866 9101_ $$0I:(DE-588b)2008985-5$$6P:(DE-H253)PIP1088561$$aDeutsches Elektronen-Synchrotron$$b0$$kDESY
000605866 9101_ $$0I:(DE-588b)2008985-5$$6P:(DE-H253)PIP1024695$$aDeutsches Elektronen-Synchrotron$$b1$$kDESY
000605866 9101_ $$0I:(DE-HGF)0$$6P:(DE-H253)PIP1097777$$aExternal Institute$$b2$$kExtern
000605866 9101_ $$0I:(DE-HGF)0$$6P:(DE-H253)PIP1015292$$aExternal Institute$$b3$$kExtern
000605866 9131_ $$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$$x0
000605866 9141_ $$y2024
000605866 9201_ $$0I:(DE-H253)CMS-20120731$$kCMS$$lLHC/CMS Experiment$$x0
000605866 980__ $$aconf
000605866 980__ $$aVDB
000605866 980__ $$aI:(DE-H253)CMS-20120731
000605866 980__ $$aUNRESTRICTED