000600286 001__ 600286
000600286 005__ 20250728212114.0
000600286 0247_ $$2doi$$a10.1103/PhysRevAccelBeams.27.054601
000600286 0247_ $$2datacite_doi$$a10.3204/PUBDB-2023-07854
000600286 0247_ $$2arXiv$$aarXiv:2401.05815
000600286 0247_ $$2altmetric$$aaltmetric:158338580
000600286 0247_ $$2WOS$$aWOS:001237562300003
000600286 0247_ $$2openalex$$aopenalex:W4399072168
000600286 037__ $$aPUBDB-2023-07854
000600286 041__ $$aEnglish
000600286 082__ $$a530
000600286 088__ $$2arXiv$$aarXiv:2401.05815
000600286 1001_ $$0P:(DE-H253)PIP1095111$$aKaiser, Jan$$b0$$eCorresponding author$$udesy
000600286 245__ $$aBridging the gap between machine learning and particle accelerator physics with high-speed, differentiable simulations
000600286 260__ $$aCollege Park, MD$$bAmerican Physical Society$$c2024
000600286 3367_ $$2DRIVER$$aarticle
000600286 3367_ $$2DataCite$$aOutput Types/Journal article
000600286 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1717145400_919014
000600286 3367_ $$2BibTeX$$aARTICLE
000600286 3367_ $$2ORCID$$aJOURNAL_ARTICLE
000600286 3367_ $$00$$2EndNote$$aJournal Article
000600286 500__ $$aPhys. Rev. Accel. Beams 27 (2024) 054601. 16 pages, 9 figures, 3 tables
000600286 520__ $$aMachine learning has emerged as a powerful solution to the modern challenges in accelerator physics. However, the limited availability of beam time, the computational cost of simulations, and the high dimensionality of optimization problems pose significant challenges in generating the required data for training state-of-the-art machine learning models. In this work, we introduce cheetah, a pytorch-based high-speed differentiable linear beam dynamics code. cheetah enables the fast collection of large datasets by reducing computation times by multiple orders of magnitude and facilitates efficient gradient-based optimization for accelerator tuning and system identification. This positions cheetah as a user-friendly, readily extensible tool that integrates seamlessly with widely adopted machine learning tools. We showcase the utility of cheetah through five examples, including reinforcement learning training, gradient-based beamline tuning, gradient-based system identification, physics-informed Bayesian optimization priors, and modular neural network surrogate modeling of space charge effects. The use of such a high-speed differentiable simulation code will simplify the development of machine learning-based methods for particle accelerators and fast-track their integration into everyday operations of accelerator facilities.
000600286 536__ $$0G:(DE-HGF)POF4-621$$a621 - Accelerator Research and Development (POF4-621)$$cPOF4-621$$fPOF IV$$x0
000600286 536__ $$0G:(DE-HGF)2020_InternLabs-0011$$aInternLabs-0011 - HIR3X - Helmholtz International Laboratory on Reliability, Repetition, Results at the most advanced X-ray Sources (2020_InternLabs-0011)$$c2020_InternLabs-0011$$x1
000600286 536__ $$0G:(DE-HGF)2020_ZT-I-PF-5-6$$aZT-I-PF-5-6 - Autonomous Accelerator (AA) (2020_ZT-I-PF-5-6)$$c2020_ZT-I-PF-5-6$$x2
000600286 542__ $$2Crossref$$i2024-05-28$$uhttps://creativecommons.org/licenses/by/4.0/
000600286 588__ $$aDataset connected to CrossRef, Journals: bib-pubdb1.desy.de
000600286 650_7 $$2INSPIRE$$aspace charge
000600286 650_7 $$2INSPIRE$$aaccelerator
000600286 650_7 $$2INSPIRE$$amachine learning
000600286 650_7 $$2INSPIRE$$aoptimization
000600286 650_7 $$2INSPIRE$$areinforcement learning
000600286 650_7 $$2INSPIRE$$amodular
000600286 650_7 $$2INSPIRE$$aBayesian
000600286 650_7 $$2INSPIRE$$aneural network
000600286 693__ $$0EXP:(DE-H253)ARES-20200101$$1EXP:(DE-H253)SINBAD-20200101$$5EXP:(DE-H253)ARES-20200101$$aSINBAD$$eAccelerator Research Experiment at SINBAD$$x0
000600286 7001_ $$aXu, Chenran$$b1
000600286 7001_ $$0P:(DE-H253)PIP1087213$$aEichler, Annika$$b2
000600286 7001_ $$aSantamaria Garcia, Andrea$$b3
000600286 77318 $$2Crossref$$3journal-article$$a10.1103/physrevaccelbeams.27.054601$$bAmerican Physical Society (APS)$$d2024-05-28$$n5$$p054601$$tPhysical Review Accelerators and Beams$$v27$$x2469-9888$$y2024
000600286 773__ $$0PERI:(DE-600)2844143-6$$a10.1103/PhysRevAccelBeams.27.054601$$gVol. 27, no. 5, p. 054601$$n5$$p054601$$tPhysical review accelerators and beams$$v27$$x2469-9888$$y2024
000600286 7870_ $$0PUBDB-2024-01950$$aKaiser, Jan et.al.$$d2024$$iIsParent$$rarXiv:2401.05815$$tBridging the gap between machine learning and particle accelerator physics with high-speed, differentiable simulations
000600286 8564_ $$uhttps://bib-pubdb1.desy.de/record/600286/files/HTML-Approval_of_scientific_publication.html
000600286 8564_ $$uhttps://bib-pubdb1.desy.de/record/600286/files/PDF-Approval_of_scientific_publication.pdf
000600286 8564_ $$uhttps://bib-pubdb1.desy.de/record/600286/files/PhysRevAccelBeams.27.054601.pdf$$yRestricted$$zStatID:(DE-HGF)0599
000600286 8564_ $$uhttps://bib-pubdb1.desy.de/record/600286/files/post-referee%20version.pdf$$yOpenAccess$$zStatID:(DE-HGF)0510
000600286 8564_ $$uhttps://bib-pubdb1.desy.de/record/600286/files/post-referee%20version.pdf?subformat=pdfa$$xpdfa$$yOpenAccess$$zStatID:(DE-HGF)0510
000600286 8564_ $$uhttps://bib-pubdb1.desy.de/record/600286/files/PhysRevAccelBeams.27.054601.pdf?subformat=pdfa$$xpdfa$$yRestricted$$zStatID:(DE-HGF)0599
000600286 8767_ $$80376077$$92024-09-13$$d2025-07-28$$eAPC$$jFlatrate
000600286 8767_ $$d2025-07-28$$eAPC$$jStorniert$$zDFG OAPK (Projekt)
000600286 8767_ $$d2025-07-28$$eAPC$$jZahlung erfolgt$$zDFG OAPK (Projekt)
000600286 909CO $$ooai:bib-pubdb1.desy.de:600286$$pVDB$$pdriver$$pOpenAPC$$popen_access$$popenaire$$popenCost$$pdnbdelivery
000600286 9101_ $$0I:(DE-588b)2008985-5$$6P:(DE-H253)PIP1095111$$aDeutsches Elektronen-Synchrotron$$b0$$kDESY
000600286 9101_ $$0I:(DE-588b)2008985-5$$6P:(DE-H253)PIP1087213$$aDeutsches Elektronen-Synchrotron$$b2$$kDESY
000600286 9101_ $$0I:(DE-588)1043621512$$6P:(DE-H253)PIP1087213$$aEuropean XFEL$$b2$$kXFEL.EU
000600286 9131_ $$0G:(DE-HGF)POF4-621$$1G:(DE-HGF)POF4-620$$2G:(DE-HGF)POF4-600$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$aDE-HGF$$bForschungsbereich Materie$$lMaterie und Technologie$$vAccelerator Research and Development$$x0
000600286 9141_ $$y2024
000600286 915__ $$0LIC:(DE-HGF)CCBY4$$2HGFVOC$$aCreative Commons Attribution CC BY 4.0
000600286 915__ $$0StatID:(DE-HGF)0501$$2StatID$$aDBCoverage$$bDOAJ Seal$$d2021-10-14T15:01:02Z
000600286 915__ $$0StatID:(DE-HGF)0500$$2StatID$$aDBCoverage$$bDOAJ$$d2021-10-14T15:01:02Z
000600286 915__ $$0StatID:(DE-HGF)0113$$2StatID$$aWoS$$bScience Citation Index Expanded$$d2023-10-27
000600286 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
000600286 915__ $$0StatID:(DE-HGF)0030$$2StatID$$aPeer Review$$bDOAJ : Anonymous peer review$$d2021-10-14T15:01:02Z
000600286 915__ $$0StatID:(DE-HGF)0160$$2StatID$$aDBCoverage$$bEssential Science Indicators$$d2023-10-27
000600286 915__ $$0StatID:(DE-HGF)0100$$2StatID$$aJCR$$bPHYS REV ACCEL BEAMS : 2022$$d2024-12-28
000600286 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS$$d2024-12-28
000600286 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bClarivate Analytics Master Journal List$$d2024-12-28
000600286 915__ $$0StatID:(DE-HGF)1150$$2StatID$$aDBCoverage$$bCurrent Contents - Physical, Chemical and Earth Sciences$$d2024-12-28
000600286 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection$$d2024-12-28
000600286 915__ $$0StatID:(DE-HGF)9900$$2StatID$$aIF < 5$$d2024-12-28
000600286 915pc $$0PC:(DE-HGF)0000$$2APC$$aAPC keys set
000600286 915pc $$0PC:(DE-HGF)0001$$2APC$$aLocal Funding
000600286 915pc $$0PC:(DE-HGF)0002$$2APC$$aDFG OA Publikationskosten
000600286 915pc $$0PC:(DE-HGF)0003$$2APC$$aDOAJ Journal
000600286 9201_ $$0I:(DE-H253)MSK-20120731$$kMSK$$lStrahlkontrollen$$x0
000600286 9801_ $$aFullTexts
000600286 980__ $$ajournal
000600286 980__ $$aVDB
000600286 980__ $$aUNRESTRICTED
000600286 980__ $$aI:(DE-H253)MSK-20120731
000600286 980__ $$aAPC
000600286 999C5 $$1J. Kaiser$$2Crossref$$oJ. Kaiser Proceedings of the 39th International Conference on Machine Learning (ICML-2022), Baltimore, Maryland 2022$$tProceedings of the 39th International Conference on Machine Learning (ICML-2022), Baltimore, Maryland$$y2022
000600286 999C5 $$1A. L. Edelen$$2Crossref$$oA. L. Edelen Proceedings of the 38th International Free-Electron Laser Conference, FEL 2017 2017$$tProceedings of the 38th International Free-Electron Laser Conference, FEL 2017$$y2017
000600286 999C5 $$2Crossref$$9-- missing cx lookup --$$a10.1109/ACCESS.2021.3132942
000600286 999C5 $$1C. Xu$$2Crossref$$oC. Xu Proceedings of the 14th International Particle Accelerator Conference, IPAC-2023, Venice, Italy 2023$$tProceedings of the 14th International Particle Accelerator Conference, IPAC-2023, Venice, Italy$$y2023
000600286 999C5 $$2Crossref$$9-- missing cx lookup --$$a10.1103/PhysRevAccelBeams.23.124801
000600286 999C5 $$2Crossref$$9-- missing cx lookup --$$a10.1038/s41586-021-04301-9
000600286 999C5 $$2Crossref$$9-- missing cx lookup --$$a10.1038/s41586-019-1724-z
000600286 999C5 $$2Crossref$$9-- missing cx lookup --$$a10.1016/j.nima.2014.09.057
000600286 999C5 $$1S. Tomin$$2Crossref$$oS. Tomin Proceedings of the 8th International Particle Accelerator Conference, IPAC-2017, Copenhagen, Denmark 2017$$tProceedings of the 8th International Particle Accelerator Conference, IPAC-2017, Copenhagen, Denmark$$y2017
000600286 999C5 $$1Z. Zhang$$2Crossref$$oZ. Zhang Proceedings of the 13th International Particle Accelerator Conference, IPAC-2022, Bangkok, Thailand 2022$$tProceedings of the 13th International Particle Accelerator Conference, IPAC-2022, Bangkok, Thailand$$y2022
000600286 999C5 $$1A. Paszke$$2Crossref$$oA. Paszke Advances in Neural Information Processing Systems 32 2019$$tAdvances in Neural Information Processing Systems 32$$y2019
000600286 999C5 $$2Crossref$$9-- missing cx lookup --$$a10.1016/j.nima.2005.11.001
000600286 999C5 $$1M. Borland$$2Crossref$$oM. Borland Proceedings of the 6th International Computational Accelerator Physics Conference, Darmstadt, Germany 2000$$tProceedings of the 6th International Computational Accelerator Physics Conference, Darmstadt, Germany$$y2000
000600286 999C5 $$1J. Gonzalez-Aguilera$$2Crossref$$oJ. Gonzalez-Aguilera Proceedings of the 14th International Particle Accelerator Conference, IPAC-2023, Venice, Italy 2023$$tProceedings of the 14th International Particle Accelerator Conference, IPAC-2023, Venice, Italy$$y2023
000600286 999C5 $$2Crossref$$9-- missing cx lookup --$$a10.1103/PhysRevApplied.16.024005
000600286 999C5 $$2Crossref$$9-- missing cx lookup --$$a10.1103/PhysRevAccelBeams.25.094601
000600286 999C5 $$2Crossref$$9-- missing cx lookup --$$a10.1103/PhysRevLett.121.044801
000600286 999C5 $$2Crossref$$9-- missing cx lookup --$$a10.1038/s41598-021-98785-0
000600286 999C5 $$2Crossref$$9-- missing cx lookup --$$a10.1016/j.revip.2023.100085
000600286 999C5 $$2Crossref$$9-- missing cx lookup --$$a10.1364/OE.432488
000600286 999C5 $$2Crossref$$9-- missing cx lookup --$$a10.1103/PhysRevLett.128.204801
000600286 999C5 $$2Crossref$$9-- missing cx lookup --$$a10.1103/PhysRevLett.130.145001
000600286 999C5 $$2Crossref$$9-- missing cx lookup --$$a10.1103/PhysRevAccelBeams.26.024601
000600286 999C5 $$1O. Stein$$2Crossref$$oO. Stein Proceedings of the 13th International Particle Accelerator Conference IPAC-2022, Bangkok, Thailand 2022$$tProceedings of the 13th International Particle Accelerator Conference IPAC-2022, Bangkok, Thailand$$y2022
000600286 999C5 $$1J. Tobin$$2Crossref$$oJ. Tobin Proceedings of the 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS-2017 2017$$tProceedings of the 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS-2017$$y2017
000600286 999C5 $$1K. L. Brown$$2Crossref$$oK. L. Brown 1968$$y1968
000600286 999C5 $$2Crossref$$9-- missing cx lookup --$$a10.1103/PhysRevE.49.1599
000600286 999C5 $$2Crossref$$9-- missing cx lookup --$$a10.3390/instruments5030028
000600286 999C5 $$1F. Burkart$$2Crossref$$oF. Burkart Proceedings of the 31st International Linear Accelerator Conference (LINAC’22), Liverpool, UK 2022$$tProceedings of the 31st International Linear Accelerator Conference (LINAC’22), Liverpool, UK$$y2022
000600286 999C5 $$1A. Eichler$$2Crossref$$oA. Eichler Proceedings of the 12th International Particle Accelerator Conference, IPAC-2021, Campinas, SP, Brazil 2021$$tProceedings of the 12th International Particle Accelerator Conference, IPAC-2021, Campinas, SP, Brazil$$y2021
000600286 999C5 $$1A. Raffin$$2Crossref$$oA. Raffin 2021$$y2021
000600286 999C5 $$2Crossref$$9-- missing cx lookup --$$a10.1109/JPROC.2015.2494218
000600286 999C5 $$2Crossref$$9-- missing cx lookup --$$a10.1103/PhysRevLett.124.124801
000600286 999C5 $$1K. Hwang$$2Crossref$$oK. Hwang Proceedings of the 13th International Particle Accelerator Conference, IPAC-2022, Bangkok, Thailand 2022$$tProceedings of the 13th International Particle Accelerator Conference, IPAC-2022, Bangkok, Thailand$$y2022
000600286 999C5 $$1M. Balandat$$2Crossref$$oM. Balandat Advances in Neural Information Processing Systems 33: 34th Annual Conference on Neural Information Processing Systems (NeurIPS-2020) 2020$$tAdvances in Neural Information Processing Systems 33: 34th Annual Conference on Neural Information Processing Systems (NeurIPS-2020)$$y2020
000600286 999C5 $$1R. Roussel$$2Crossref$$oR. Roussel Proceedings of the 14th International Particle Accelerator Conference, IPAC-2023, Venice, Italy 2023$$tProceedings of the 14th International Particle Accelerator Conference, IPAC-2023, Venice, Italy$$y2023