000593578 001__ 593578
000593578 005__ 20240707063342.0
000593578 0247_ $$2INSPIRETeX$$aBuhmann:2023kdg
000593578 0247_ $$2inspire$$ainspire:2696622
000593578 0247_ $$2arXiv$$aarXiv:2309.05704
000593578 0247_ $$2datacite_doi$$a10.3204/PUBDB-2023-05463
000593578 037__ $$aPUBDB-2023-05463
000593578 041__ $$aEnglish
000593578 088__ $$2DESY$$aDESY-23-130
000593578 088__ $$2arXiv$$aarXiv:2309.05704
000593578 1001_ $$0P:(DE-H253)PIP1018807$$aBuhmann, Erik$$b0$$eCorresponding author
000593578 245__ $$aCaloClouds II: Ultra-Fast Geometry-Independent Highly-Granular Calorimeter Simulation
000593578 260__ $$c2023
000593578 3367_ $$0PUB:(DE-HGF)25$$2PUB:(DE-HGF)$$aPreprint$$bpreprint$$mpreprint$$s1698850195_1121333
000593578 3367_ $$2ORCID$$aWORKING_PAPER
000593578 3367_ $$028$$2EndNote$$aElectronic Article
000593578 3367_ $$2DRIVER$$apreprint
000593578 3367_ $$2BibTeX$$aARTICLE
000593578 3367_ $$2DataCite$$aOutput Types/Working Paper
000593578 500__ $$a30 pages, 7 figures, 3 tables, code available at https://github.com/FLC-QU-hep/CaloClouds-2
000593578 520__ $$aFast simulation of the energy depositions in high-granular detectors is needed for future collider experiments with ever increasing luminosities. Generative machine learning (ML) models have been shown to speed up and augment the traditional simulation chain in physics analysis. However, the majority of previous efforts were limited to models relying on fixed, regular detector readout geometries. A major advancement is the recently introduced CaloClouds model, a geometry-independent diffusion model, which generates calorimeter showers as point clouds for the electromagnetic calorimeter of the envisioned International Large Detector (ILD). In this work, we introduce CaloClouds II which features a number of key improvements. This includes continuous time score-based modelling, which allows for a 25 step sampling with comparable fidelity to CaloClouds while yielding a $6\times$ speed-up over Geant4 on a single CPU ($5\times$ over CaloClouds). We further distill the diffusion model into a consistency model allowing for accurate sampling in a single step and resulting in a $46\times$ ($37\times$) speed-up. This constitutes the first application of consistency distillation for the generation of calorimeter showers.
000593578 536__ $$0G:(DE-HGF)POF4-623$$a623 - Data Management and Analysis (POF4-623)$$cPOF4-623$$fPOF IV$$x0
000593578 536__ $$0G:(EU-Grant)101004761$$aAIDAinnova - Advancement and Innovation for Detectors at Accelerators (101004761)$$c101004761$$fH2020-INFRAINNOV-2020-2$$x1
000593578 536__ $$0G:(DE-Ds200)BMBF-05D23GU4$$a05D23GU4 - Verbundprojekt 05D2022 - KISS: Künstliche Intelligenz zur schnellen Simulation von wissenschaftlichen Daten. Teilprojekt 1. (BMBF-05D23GU4)$$cBMBF-05D23GU4$$f05D23GU4$$x2
000593578 588__ $$aDataset connected to INSPIRE
000593578 650_7 $$2INSPIRE$$adiffusion, model
000593578 650_7 $$2INSPIRE$$acalorimeter, electromagnetic
000593578 650_7 $$2INSPIRE$$ashowers
000593578 650_7 $$2INSPIRE$$ageometry
000593578 650_7 $$2INSPIRE$$areadout
000593578 650_7 $$2INSPIRE$$amachine learning
000593578 650_7 $$2INSPIRE$$aILD detector
000593578 650_7 $$2INSPIRE$$acloud
000593578 693__ $$0EXP:(DE-MLZ)NOSPEC-20140101$$5EXP:(DE-MLZ)NOSPEC-20140101$$eNo specific instrument$$x0
000593578 7001_ $$0P:(DE-H253)PIP1002530$$aGaede, Frank$$b1
000593578 7001_ $$0P:(DE-H253)PIP1081743$$aKasieczka, Gregor$$b2
000593578 7001_ $$0P:(DE-H253)PIP1090878$$aKorol, Anatolii$$b3
000593578 7001_ $$0P:(DE-H253)PIP1094581$$aKorcari, William$$b4
000593578 7001_ $$0P:(DE-H253)PIP1000475$$aKrüger, Katja$$b5
000593578 7001_ $$0P:(DE-H253)PIP1030902$$aMcKeown, Peter$$b6
000593578 8564_ $$uhttps://bib-pubdb1.desy.de/record/593578/files/HTML-Approval_of_scientific_publication.html
000593578 8564_ $$uhttps://bib-pubdb1.desy.de/record/593578/files/PDF-Approval_of_scientific_publication.pdf
000593578 8564_ $$uhttps://bib-pubdb1.desy.de/record/593578/files/2309.05704v1.pdf$$yOpenAccess
000593578 8564_ $$uhttps://bib-pubdb1.desy.de/record/593578/files/2309.05704v1.pdf?subformat=pdfa$$xpdfa$$yOpenAccess
000593578 909CO $$ooai:bib-pubdb1.desy.de:593578$$pdnbdelivery$$pec_fundedresources$$pVDB$$pdriver$$popen_access$$popenaire
000593578 9101_ $$0I:(DE-HGF)0$$6P:(DE-H253)PIP1018807$$aExternal Institute$$b0$$kExtern
000593578 9101_ $$0I:(DE-588b)2008985-5$$6P:(DE-H253)PIP1002530$$aDeutsches Elektronen-Synchrotron$$b1$$kDESY
000593578 9101_ $$0I:(DE-HGF)0$$6P:(DE-H253)PIP1081743$$aExternal Institute$$b2$$kExtern
000593578 9101_ $$0I:(DE-588b)2008985-5$$6P:(DE-H253)PIP1090878$$aDeutsches Elektronen-Synchrotron$$b3$$kDESY
000593578 9101_ $$0I:(DE-HGF)0$$6P:(DE-H253)PIP1090878$$aExternal Institute$$b3$$kExtern
000593578 9101_ $$0I:(DE-HGF)0$$6P:(DE-H253)PIP1094581$$aExternal Institute$$b4$$kExtern
000593578 9101_ $$0I:(DE-588b)2008985-5$$6P:(DE-H253)PIP1000475$$aDeutsches Elektronen-Synchrotron$$b5$$kDESY
000593578 9101_ $$0I:(DE-588b)2008985-5$$6P:(DE-H253)PIP1030902$$aDeutsches Elektronen-Synchrotron$$b6$$kDESY
000593578 9131_ $$0G:(DE-HGF)POF4-623$$1G:(DE-HGF)POF4-620$$2G:(DE-HGF)POF4-600$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$aDE-HGF$$bForschungsbereich Materie$$lMaterie und Technologie$$vData Management and Analysis$$x0
000593578 9141_ $$y2023
000593578 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
000593578 915__ $$0StatID:(DE-HGF)0580$$2StatID$$aPublished
000593578 9201_ $$0I:(DE-H253)FTX-20210408$$kFTX$$lTechnol. zukünft. Teilchenph. Experim.$$x0
000593578 980__ $$apreprint
000593578 980__ $$aVDB
000593578 980__ $$aUNRESTRICTED
000593578 980__ $$aI:(DE-H253)FTX-20210408
000593578 9801_ $$aFullTexts