000627945 001__ 627945
000627945 005__ 20250519183529.0
000627945 0247_ $$2doi$$a10.21468/SciPostPhysCore.8.1.021
000627945 037__ $$aPUBDB-2025-01693
000627945 1001_ $$0P:(DE-H253)PIP1028713$$aWolf, Moritz$$b0
000627945 245__ $$aFast Perfekt: Regression-based refinement of fast simulation
000627945 260__ $$aAmsterdam$$bSciPost Foundation$$c2025
000627945 3367_ $$2DRIVER$$aarticle
000627945 3367_ $$2DataCite$$aOutput Types/Journal article
000627945 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1747633602_396519
000627945 3367_ $$2BibTeX$$aARTICLE
000627945 3367_ $$2ORCID$$aJOURNAL_ARTICLE
000627945 3367_ $$00$$2EndNote$$aJournal Article
000627945 520__ $$aThe availability of precise and accurate simulation is a limiting factor for interpreting and forecasting data in many fields of science and engineering. Often, one or more distinct simulation software applications are developed, each with a relative advantage in accuracy or speed. The quality of insights extracted from the data stands to increase if the accuracy of faster, more economical simulation could be improved to parity or near parity with more resource-intensive but accurate simulation. We present Fast Perfekt, a machine-learned regression to refine the output of fast simulation that employs residual neural networks. A deterministic morphing model is trained using a unique schedule that makes use of the ensemble loss function MMD, with the option of an additional pair-based loss function such as the MSE. We explore this methodology in the context of an abstract analytical model and in terms of a realistic particle physics application featuring jet properties in hadron collisions at the CERN Large Hadron Collider. The refinement makes maximum use of existing domain knowledge, and introduces minimal computational overhead to production.
000627945 536__ $$0G:(DE-HGF)2019_IVF-HIDSS-0002$$aHIDSS-0002 - DASHH: Data Science in Hamburg - Helmholtz Graduate School for the Structure of Matter (2019_IVF-HIDSS-0002)$$c2019_IVF-HIDSS-0002$$x0
000627945 588__ $$aDataset connected to CrossRef, Journals: bib-pubdb1.desy.de
000627945 7001_ $$0P:(DE-H253)PIP1105565$$aStietz, Lars Olaf$$b1
000627945 7001_ $$0P:(DE-H253)PIP1023675$$aConnor, Patrick$$b2
000627945 7001_ $$0P:(DE-H253)PIP1004211$$aSchleper, Peter$$b3
000627945 7001_ $$0P:(DE-H253)PIP1031825$$aBein, Samuel$$b4
000627945 773__ $$0PERI:(DE-600)3071450-3$$a10.21468/SciPostPhysCore.8.1.021$$gVol. 8, no. 1, p. 021$$n1$$p021$$tSciPost Physics Core$$v8$$x2666-9366$$y2025
000627945 8564_ $$uhttps://bib-pubdb1.desy.de/record/627945/files/SciPostPhysCore_8_1_021.pdf$$yRestricted
000627945 8564_ $$uhttps://bib-pubdb1.desy.de/record/627945/files/SciPostPhysCore_8_1_021.pdf?subformat=pdfa$$xpdfa$$yRestricted
000627945 9101_ $$0I:(DE-HGF)0$$6P:(DE-H253)PIP1028713$$aExternal Institute$$b0$$kExtern
000627945 9101_ $$0I:(DE-HGF)0$$6P:(DE-H253)PIP1105565$$aExternal Institute$$b1$$kExtern
000627945 9101_ $$0I:(DE-HGF)0$$6P:(DE-H253)PIP1023675$$aExternal Institute$$b2$$kExtern
000627945 9101_ $$0I:(DE-HGF)0$$6P:(DE-H253)PIP1004211$$aExternal Institute$$b3$$kExtern
000627945 9101_ $$0I:(DE-HGF)0$$6P:(DE-H253)PIP1031825$$aExternal Institute$$b4$$kExtern
000627945 915__ $$0StatID:(DE-HGF)0100$$2StatID$$aJCR$$bSCIPOST PHYSICS CORE : 2022$$d2025-01-01
000627945 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS$$d2025-01-01
000627945 915__ $$0StatID:(DE-HGF)0501$$2StatID$$aDBCoverage$$bDOAJ Seal$$d2020-04-30T11:42:11Z
000627945 915__ $$0StatID:(DE-HGF)0500$$2StatID$$aDBCoverage$$bDOAJ$$d2020-04-30T11:42:11Z
000627945 915__ $$0StatID:(DE-HGF)0030$$2StatID$$aPeer Review$$bDOAJ : Open peer review$$d2020-04-30T11:42:11Z
000627945 915__ $$0LIC:(DE-HGF)CCBYNV$$2V:(DE-HGF)$$aCreative Commons Attribution CC BY (No Version)$$bDOAJ$$d2020-04-30T11:42:11Z
000627945 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bClarivate Analytics Master Journal List$$d2025-01-01
000627945 915__ $$0StatID:(DE-HGF)0112$$2StatID$$aWoS$$bEmerging Sources Citation Index$$d2025-01-01
000627945 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection$$d2025-01-01
000627945 915__ $$0StatID:(DE-HGF)9900$$2StatID$$aIF < 5$$d2025-01-01
000627945 9801_ $$aEXTERN4COORD
000627945 980__ $$ajournal
000627945 980__ $$aUSER
000627945 980__ $$aI:(DE-H253)FS_DOOR-User-20241023
000627945 980__ $$aI:(DE-H253)DESY-20170408
000627945 980__ $$aI:(DE-H253)FS-TUX-20170422