{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T04:22:55Z","timestamp":1780546975721,"version":"3.54.1"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2022,11,23]],"date-time":"2022-11-23T00:00:00Z","timestamp":1669161600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,11,23]],"date-time":"2022-11-23T00:00:00Z","timestamp":1669161600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100007569","name":"Carl-Zeiss-Stiftung","doi-asserted-by":"publisher","award":["DeepTurb"],"award-info":[{"award-number":["DeepTurb"]}],"id":[{"id":"10.13039\/100007569","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","award":["289034702"],"award-info":[{"award-number":["289034702"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","award":["430154635"],"award-info":[{"award-number":["430154635"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","award":["WO2056\/6-1"],"award-info":[{"award-number":["WO2056\/6-1"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Nonlinear Sci"],"published-print":{"date-parts":[[2023,2]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>The Koopman operator has become an essential tool for data-driven approximation of dynamical (control) systems, e.g., via extended dynamic mode decomposition. Despite its popularity, convergence results and, in particular, error bounds are still scarce. In this paper, we derive probabilistic bounds for the approximation error and the prediction error depending on the number of training data points, for both ordinary and stochastic differential equations while using either ergodic trajectories or i.i.d. samples. We illustrate these bounds by means of an example with the Ornstein\u2013Uhlenbeck process. Moreover, we extend our analysis to (stochastic) nonlinear control-affine systems. We prove error estimates for a previously proposed approach that exploits the linearity of the Koopman generator to obtain a bilinear surrogate control system and, thus, circumvents the curse of dimensionality since the system is not autonomized by augmenting the state by the control inputs. To the best of our knowledge, this is the first finite-data error analysis in the stochastic and\/or control setting. Finally, we demonstrate the effectiveness of the bilinear approach by comparing it with state-of-the-art techniques showing its superiority whenever state and control are coupled.<\/jats:p>","DOI":"10.1007\/s00332-022-09862-1","type":"journal-article","created":{"date-parts":[[2022,11,24]],"date-time":"2022-11-24T17:45:26Z","timestamp":1669311926000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":62,"title":["Finite-Data Error Bounds for Koopman-Based Prediction and Control"],"prefix":"10.1007","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2444-7889","authenticated-orcid":false,"given":"Feliks","family":"N\u00fcske","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3389-793X","authenticated-orcid":false,"given":"Sebastian","family":"Peitz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4670-8894","authenticated-orcid":false,"given":"Friedrich","family":"Philipp","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8081-5108","authenticated-orcid":false,"given":"Manuel","family":"Schaller","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1450-2373","authenticated-orcid":false,"given":"Karl","family":"Worthmann","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,11,23]]},"reference":[{"key":"9862_CR1","volume-title":"Analysis and geometry of Markov diffusion operators","author":"D Bakry","year":"2013","unstructured":"Bakry, D., Gentil, I., Ledoux, M.: Analysis and geometry of Markov diffusion operators, vol. 348. Springer Science & Business Media, Berlin (2013)"},{"issue":"6","key":"9862_CR2","doi-asserted-by":"publisher","first-page":"1049","DOI":"10.1090\/S0002-9939-1957-0098162-6","volume":"8","author":"A Beck","year":"1957","unstructured":"Beck, A., Schwartz, J.T.: A vector-valued random ergodic theorem. Proc. Am. Math. Soc. 8(6), 1049\u20131059 (1957)","journal-title":"Proc. Am. Math. Soc."},{"issue":"8","key":"9862_CR3","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1016\/j.sysconle.2014.08.002","volume":"72","author":"A Boccia","year":"2014","unstructured":"Boccia, A., Gr\u00fcne, L., Worthmann, K.: Stability and feasibility of state constrained MPC without stabilizing terminal constraints. Syst. Control Lett. 72(8), 14\u201321 (2014)","journal-title":"Syst. Control Lett."},{"issue":"3","key":"9862_CR4","doi-asserted-by":"publisher","first-page":"4369","DOI":"10.1109\/LRA.2021.3068117","volume":"6","author":"D Bruder","year":"2021","unstructured":"Bruder, D., Fu, X., Vasudevan, R.: Advantages of bilinear Koopman realizations for the modeling and control of systems with unknown dynamics. IEEE Robot. Autom. Lett. 6(3), 4369\u20134376 (2021)","journal-title":"IEEE Robot. Autom. Lett."},{"issue":"2","key":"9862_CR5","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1137\/21M1401243","volume":"64","author":"SL Brunton","year":"2022","unstructured":"Brunton, S.L., Budi\u0161i\u0107, M., Kaiser, E., Kutz, J.N.: Modern Koopman theory for dynamical systems. SIAM Rev. 64(2), 229\u2013340 (2022)","journal-title":"SIAM Rev."},{"key":"9862_CR6","doi-asserted-by":"publisher","first-page":"3932","DOI":"10.1073\/pnas.1517384113","volume":"113","author":"SL Brunton","year":"2016","unstructured":"Brunton, S.L., Proctor, J.L., Kutz, J.N.: Discovering governing equations from data by sparse identification of nonlinear dynamical systems. Proc. Natl. Acad. Sci. 113, 3932\u20133937 (2016)","journal-title":"Proc. Natl. Acad. Sci."},{"key":"9862_CR7","volume-title":"Ordinary Differ. Equ. Appl.","author":"C Chicone","year":"2006","unstructured":"Chicone, C.: Ordinary Differ. Equ. Appl., vol. 34. Springer Science & Business Media, New York (2006)"},{"issue":"3","key":"9862_CR8","doi-asserted-by":"publisher","first-page":"457","DOI":"10.1007\/s10955-016-1491-2","volume":"163","author":"AB Duncan","year":"2016","unstructured":"Duncan, A.B., Lelievre, T., Pavliotis, G.A.: Variance reduction using nonreversible Langevin samplers. J. Stat. Phys. 163(3), 457\u2013491 (2016)","journal-title":"J. Stat. Phys."},{"issue":"1","key":"9862_CR9","doi-asserted-by":"publisher","first-page":"265","DOI":"10.1109\/LCSYS.2020.3001514","volume":"5","author":"W Esterhuizen","year":"2020","unstructured":"Esterhuizen, W., Worthmann, K., Streif, S.: Recursive feasibility of continuous-time model predictive control without stabilising constraints. IEEE Control Syst. Lett. 5(1), 265\u2013270 (2020)","journal-title":"IEEE Control Syst. Lett."},{"key":"9862_CR10","doi-asserted-by":"crossref","unstructured":"Goswami, D., Paley, D.A.: Global bilinearization and controllability of control-affine nonlinear systems: a Koopman spectral approach. In 2017 IEEE 56th Annual Conference on Decision and Control (CDC), pp. 6107\u20136112. IEEE (2017)","DOI":"10.1109\/CDC.2017.8264582"},{"key":"9862_CR11","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/abf0f5","volume":"2","author":"E Kaiser","year":"2021","unstructured":"Kaiser, E., Kutz, J.N., Brunton, S.L.: Data-driven discovery of Koopman eigenfunctions for control. Mach. Learn. Sci. Technol. 2, 035023 (2021)","journal-title":"Mach. Learn. Sci. Technol."},{"issue":"1","key":"9862_CR12","first-page":"51","volume":"3","author":"S Klus","year":"2016","unstructured":"Klus, S., Koltai, P., Sch\u00fctte, C.: On the numerical approximation of the Perron\u2013Frobenius and Koopman operator. J. Comput. Dyn. 3(1), 51\u201379 (2016)","journal-title":"J. Comput. Dyn."},{"key":"9862_CR13","doi-asserted-by":"publisher","DOI":"10.1088\/1751-8121\/ac7d22","volume":"31","author":"S Klus","year":"2022","unstructured":"Klus, S., N\u00fcske, F., Peitz, S.: Koopman analysis of quantum systems. J. Phys. A. 31, 314002 (2022)","journal-title":"J. Phys. A."},{"issue":"7","key":"9862_CR14","doi-asserted-by":"publisher","first-page":"722","DOI":"10.3390\/e22070722","volume":"22","author":"S Klus","year":"2020","unstructured":"Klus, S., N\u00fcske, F., Hamzi, B.: Kernel-based approximation of the Koopman Generator and Schr\u00f6dinger Operator. Entropy 22(7), 722 (2020)","journal-title":"Entropy"},{"issue":"3","key":"9862_CR15","doi-asserted-by":"publisher","first-page":"985","DOI":"10.1007\/s00332-017-9437-7","volume":"28","author":"S Klus","year":"2018","unstructured":"Klus, S., N\u00fcske, F., Koltai, P., Wu, H., Kevrekidis, I., Sch\u00fctte, C., No\u00e9, F.: Data-driven model reduction and transfer operator approximation. J. Nonlinear Sci. 28(3), 985\u20131010 (2018)","journal-title":"J. Nonlinear Sci."},{"key":"9862_CR16","doi-asserted-by":"publisher","DOI":"10.1016\/j.physd.2020.132416","volume":"406","author":"S Klus","year":"2020","unstructured":"Klus, S., N\u00fcske, F., Peitz, S., Niemann, J.-H., Clementi, C., Sch\u00fctte, C.: Data-driven approximation of the Koopman generator: model reduction, system identification, and control. Phys. D 406, 132416 (2020)","journal-title":"Phys. D"},{"issue":"5","key":"9862_CR17","doi-asserted-by":"publisher","first-page":"315","DOI":"10.1073\/pnas.17.5.315","volume":"17","author":"BO Koopman","year":"1931","unstructured":"Koopman, B.O.: Hamiltonian systems and transformations in Hilbert space. Proc. Natl. Acad. Sci. 17(5), 315\u2013318 (1931)","journal-title":"Proc. Natl. Acad. Sci."},{"key":"9862_CR18","doi-asserted-by":"publisher","first-page":"149","DOI":"10.1016\/j.automatica.2018.03.046","volume":"93","author":"M Korda","year":"2018","unstructured":"Korda, M., Mezi\u0107, I.: Linear predictors for nonlinear dynamical systems: Koopman operator meets model predictive control. Automatica 93, 149\u2013160 (2018)","journal-title":"Automatica"},{"issue":"2","key":"9862_CR19","doi-asserted-by":"publisher","first-page":"687","DOI":"10.1007\/s00332-017-9423-0","volume":"28","author":"M Korda","year":"2018","unstructured":"Korda, M., Mezi\u0107, I.: On convergence of extended dynamic mode decomposition to the Koopman operator. J. Nonlinear Sci. 28(2), 687\u2013710 (2018)","journal-title":"J. Nonlinear Sci."},{"key":"9862_CR20","unstructured":"Kurdila, A.J., Bobade, P.: Koopman theory and linear approximation spaces. arXiv:1811.10809 (2018)"},{"key":"9862_CR21","doi-asserted-by":"publisher","first-page":"681","DOI":"10.1017\/S0962492916000039","volume":"25","author":"T Leli\u00e8vre","year":"2016","unstructured":"Leli\u00e8vre, T., Stoltz, G.: Partial differential equations and stochastic methods in molecular dynamics. Acta Numer. 25, 681\u2013880 (2016)","journal-title":"Acta Numer."},{"issue":"3","key":"9862_CR22","doi-asserted-by":"publisher","first-page":"1639","DOI":"10.1137\/19M1259948","volume":"42","author":"H Lu","year":"2020","unstructured":"Lu, H., Tartakovsky, D.M.: Predictive accuracy of dynamic mode decomposition. SIAM J. Sci. Comput. 42(3), 1639\u20131662 (2020)","journal-title":"SIAM J. Sci. Comput."},{"key":"9862_CR23","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2021.110550","volume":"444","author":"H Lu","year":"2021","unstructured":"Lu, H., Tartakovsky, D.M.: Extended dynamic mode decomposition for inhomogeneous problems. J. Comput. Phys. 444, 110550 (2021)","journal-title":"J. Comput. Phys."},{"key":"9862_CR24","doi-asserted-by":"crossref","unstructured":"Lu, Q., Shin, S., Zavala, V.M.: Characterizing the predictive accuracy of dynamic mode decomposition for data-driven control. IFAC-PapersOnLine 53(2), 11289\u201311294 (2020). 21th IFAC World Congress","DOI":"10.1016\/j.ifacol.2020.12.373"},{"issue":"6","key":"9862_CR25","doi-asserted-by":"publisher","first-page":"2173","DOI":"10.1109\/TRO.2021.3076581","volume":"37","author":"G Mamakoukas","year":"2021","unstructured":"Mamakoukas, G., Castano, M.L., Tan, X., Murphey, T.D.: Derivative-based koopman operators for real-time control of robotic systems. IEEE Trans. Robot. 37(6), 2173\u20132192 (2021)","journal-title":"IEEE Trans. Robot."},{"key":"9862_CR26","doi-asserted-by":"publisher","first-page":"309","DOI":"10.1007\/s11071-005-2824-x","volume":"41","author":"I Mezi\u0107","year":"2005","unstructured":"Mezi\u0107, I.: Spectral properties of dynamical systems, model reduction and decompositions. Nonlinear Dyn. 41, 309\u2013325 (2005)","journal-title":"Nonlinear Dyn."},{"key":"9862_CR27","unstructured":"Mollenhauer, M., Klus, S., Sch\u00fctte, C., Koltai, P.: Kernel autocovariance operators of stationary processes: estimation and convergence. arXiv:2004.00891, (2020)"},{"key":"9862_CR28","volume-title":"Stochastic Differential Equations: An Introduction with Applications","author":"B Oksendal","year":"2013","unstructured":"Oksendal, B.: Stochastic Differential Equations: An Introduction with Applications. Springer Science & Business Media, New York (2013)"},{"key":"9862_CR29","unstructured":"Peitz, S., Bieker, K.: On the universal transformation of data-driven models to control systems. Automatica arXiv:2021.04722, (2021)"},{"key":"9862_CR30","doi-asserted-by":"publisher","first-page":"184","DOI":"10.1016\/j.automatica.2019.05.016","volume":"106","author":"S Peitz","year":"2019","unstructured":"Peitz, S., Klus, S.: Koopman operator-based model reduction for switched-system control of PDEs. Automatica 106, 184\u2013191 (2019)","journal-title":"Automatica"},{"key":"9862_CR31","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1007\/978-3-030-35713-9_10","volume-title":"The Koopman Operator in Systems and Control: Concepts, Methodologies and Applications","author":"S Peitz","year":"2020","unstructured":"Peitz, S., Klus, S.: Feedback control of nonlinear PDEs using data-efficient reduced order models based on the Koopman operator. In: Mauroy, A., Mezi\u0107, I., Suzuki, Y. (eds.) The Koopman Operator in Systems and Control: Concepts, Methodologies and Applications, pp. 257\u2013282. Springer, Cham (2020)"},{"issue":"3","key":"9862_CR32","doi-asserted-by":"publisher","first-page":"2162","DOI":"10.1137\/20M1325678","volume":"19","author":"S Peitz","year":"2020","unstructured":"Peitz, S., Otto, S.E., Rowley, C.W.: Data-driven model predictive control using interpolated Koopman generators. SIAM J. Appl. Dyn. Syst. 19(3), 2162\u20132193 (2020)","journal-title":"SIAM J. Appl. Dyn. Syst."},{"issue":"1","key":"9862_CR33","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1137\/15M1013857","volume":"15","author":"JL Proctor","year":"2016","unstructured":"Proctor, J.L., Brunton, S.L., Kutz, J.N.: Dynamic mode decomposition with control. SIAM J. Appl. Dyn. Syst. 15(1), 142\u2013161 (2016)","journal-title":"SIAM J. Appl. Dyn. Syst."},{"issue":"1","key":"9862_CR34","doi-asserted-by":"publisher","first-page":"909","DOI":"10.1137\/16M1062296","volume":"17","author":"JL Proctor","year":"2018","unstructured":"Proctor, J.L., Brunton, S.L., Kutz, J.N.: Generalizing Koopman Theory to allow for inputs and control. SIAM J. Appl. Dyn. Syst. 17(1), 909\u2013930 (2018)","journal-title":"SIAM J. Appl. Dyn. Syst."},{"key":"9862_CR35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-61544-3_4","volume-title":"The Fokker\u2013Planck Equation","author":"H Risken","year":"1996","unstructured":"Risken, H.: The Fokker\u2013Planck Equation. Springer, Berlin (1996)"},{"key":"9862_CR36","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1017\/S0022112009992059","volume":"641","author":"CW Rowley","year":"2009","unstructured":"Rowley, C.W., Mezi\u0107, I., Bagheri, S., Schlatter, P., Henningson, D.S.: Spectral analysis of nonlinear flows. J. Fluid Mech. 641, 115\u2013127 (2009)","journal-title":"J. Fluid Mech."},{"key":"9862_CR37","doi-asserted-by":"crossref","unstructured":"Schaller, M., Worthmann, K., N\u00fcske, F., Peitz, S., Philipp, F.: Towards reliable data-based optimal and predictive control using extended DMD. IFAC-PapersOnLine arXiv:2202.09084, (2022)","DOI":"10.1016\/j.ifacol.2023.02.029"},{"key":"9862_CR38","doi-asserted-by":"publisher","first-page":"196865","DOI":"10.1109\/ACCESS.2020.3034077","volume":"8","author":"F van Breugel","year":"2020","unstructured":"van Breugel, F., Kutz, J.N., Brunton, B.W.: Numerical differentiation of noisy data: a unifying multi-objective optimization framework. IEEE Access 8, 196865\u2013196877 (2020)","journal-title":"IEEE Access"},{"issue":"1","key":"9862_CR39","doi-asserted-by":"publisher","first-page":"225","DOI":"10.1137\/20M1335984","volume":"3","author":"RJ Webber","year":"2021","unstructured":"Webber, R.J., Thiede, E.H., Dow, D., Dinner, A.R., Weare, J.: Error bounds for dynamical spectral estimation. SIAM J. Math. Data Sci. 3(1), 225\u2013252 (2021)","journal-title":"SIAM J. Math. Data Sci."},{"issue":"6","key":"9862_CR40","doi-asserted-by":"publisher","first-page":"1307","DOI":"10.1007\/s00332-015-9258-5","volume":"25","author":"MO Williams","year":"2015","unstructured":"Williams, M.O., Kevrekidis, I.G., Rowley, C.W.: A data-driven approximation of the Koopman operator: extending dynamic mode decomposition. J. Nonlinear Sci. 25(6), 1307\u20131346 (2015)","journal-title":"J. Nonlinear Sci."},{"key":"9862_CR41","unstructured":"Zhang, C., Zuazua, E.: A quantitative analysis of Koopman operator methods for system identification and predictions. (2021) arXiv:hal-0327.8445"}],"container-title":["Journal of Nonlinear Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00332-022-09862-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00332-022-09862-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00332-022-09862-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T18:13:12Z","timestamp":1701454392000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00332-022-09862-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,23]]},"references-count":41,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2023,2]]}},"alternative-id":["9862"],"URL":"https:\/\/doi.org\/10.1007\/s00332-022-09862-1","relation":{},"ISSN":["0938-8974","1432-1467"],"issn-type":[{"value":"0938-8974","type":"print"},{"value":"1432-1467","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,11,23]]},"assertion":[{"value":"26 August 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 September 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 November 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"14"}}