{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T07:56:56Z","timestamp":1774511816976,"version":"3.50.1"},"reference-count":46,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2020,9,12]],"date-time":"2020-09-12T00:00:00Z","timestamp":1599868800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2020,9,12]],"date-time":"2020-09-12T00:00:00Z","timestamp":1599868800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"crossref","award":["CRC 1114"],"award-info":[{"award-number":["CRC 1114"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100000086","name":"Directorate for Mathematical and Physical Sciences","doi-asserted-by":"publisher","award":["DMS-1127914"],"award-info":[{"award-number":["DMS-1127914"]}],"id":[{"id":"10.13039\/100000086","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002347","name":"Bundesministerium f\u00fcr Bildung und Forschung","doi-asserted-by":"publisher","award":["01IS18052B"],"award-info":[{"award-number":["01IS18052B"]}],"id":[{"id":"10.13039\/501100002347","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000781","name":"European Research Council","doi-asserted-by":"publisher","award":["757275"],"award-info":[{"award-number":["757275"]}],"id":[{"id":"10.13039\/501100000781","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Stat Comput"],"published-print":{"date-parts":[[2020,11]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>A recently introduced class of probabilistic (uncertainty-aware) solvers for ordinary differential equations (ODEs) applies Gaussian (Kalman) filtering to initial value problems. These methods model the true solution<jats:italic>x<\/jats:italic>and its first<jats:italic>q<\/jats:italic>derivatives<jats:italic>a priori<\/jats:italic>as a Gauss\u2013Markov process<jats:inline-formula><jats:alternatives><jats:tex-math>$${\\varvec{X}}$$<\/jats:tex-math><mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\"><mml:mrow><mml:mi>X<\/mml:mi><\/mml:mrow><\/mml:math><\/jats:alternatives><\/jats:inline-formula>, which is then iteratively conditioned on information about<jats:inline-formula><jats:alternatives><jats:tex-math>$${\\dot{x}}$$<\/jats:tex-math><mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\"><mml:mover><mml:mi>x<\/mml:mi><mml:mo>\u02d9<\/mml:mo><\/mml:mover><\/mml:math><\/jats:alternatives><\/jats:inline-formula>. This article establishes worst-case local convergence rates of order<jats:inline-formula><jats:alternatives><jats:tex-math>$$q+1$$<\/jats:tex-math><mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\"><mml:mrow><mml:mi>q<\/mml:mi><mml:mo>+<\/mml:mo><mml:mn>1<\/mml:mn><\/mml:mrow><\/mml:math><\/jats:alternatives><\/jats:inline-formula>for a wide range of versions of this Gaussian ODE filter, as well as global convergence rates of order<jats:italic>q<\/jats:italic>in the case of<jats:inline-formula><jats:alternatives><jats:tex-math>$$q=1$$<\/jats:tex-math><mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\"><mml:mrow><mml:mi>q<\/mml:mi><mml:mo>=<\/mml:mo><mml:mn>1<\/mml:mn><\/mml:mrow><\/mml:math><\/jats:alternatives><\/jats:inline-formula>and an integrated Brownian motion prior, and analyses how inaccurate information on<jats:inline-formula><jats:alternatives><jats:tex-math>$${\\dot{x}}$$<\/jats:tex-math><mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\"><mml:mover><mml:mi>x<\/mml:mi><mml:mo>\u02d9<\/mml:mo><\/mml:mover><\/mml:math><\/jats:alternatives><\/jats:inline-formula>coming from approximate evaluations of<jats:italic>f<\/jats:italic>affects these rates. Moreover, we show that, in the globally convergent case, the posterior credible intervals are well calibrated in the sense that they globally contract at the same rate as the truncation error. We illustrate these theoretical results by numerical experiments which might indicate their generalizability to<jats:inline-formula><jats:alternatives><jats:tex-math>$$q \\in \\{2,3,\\ldots \\}$$<\/jats:tex-math><mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\"><mml:mrow><mml:mi>q<\/mml:mi><mml:mo>\u2208<\/mml:mo><mml:mo>{<\/mml:mo><mml:mn>2<\/mml:mn><mml:mo>,<\/mml:mo><mml:mn>3<\/mml:mn><mml:mo>,<\/mml:mo><mml:mo>\u2026<\/mml:mo><mml:mo>}<\/mml:mo><\/mml:mrow><\/mml:math><\/jats:alternatives><\/jats:inline-formula>.<\/jats:p>","DOI":"10.1007\/s11222-020-09972-4","type":"journal-article","created":{"date-parts":[[2020,9,12]],"date-time":"2020-09-12T03:47:28Z","timestamp":1599882448000},"page":"1791-1816","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["Convergence rates of Gaussian ODE filters"],"prefix":"10.1007","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2782-868X","authenticated-orcid":false,"given":"Hans","family":"Kersting","sequence":"first","affiliation":[]},{"given":"T. J.","family":"Sullivan","sequence":"additional","affiliation":[]},{"given":"Philipp","family":"Hennig","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,9,12]]},"reference":[{"issue":"4","key":"9972_CR1","doi-asserted-by":"publisher","first-page":"907","DOI":"10.1007\/s11222-020-09926-w","volume":"30","author":"A Abdulle","year":"2020","unstructured":"Abdulle, A., Garegnani, G.: Random time step probabilistic methods for uncertainty quantification in chaotic and geometric numerical integration. Stat. Comput. 30(4), 907\u2013932 (2020)","journal-title":"Stat. Comput."},{"key":"9972_CR2","volume-title":"Optimal Filtering","author":"B Anderson","year":"1979","unstructured":"Anderson, B., Moore, J.: Optimal Filtering. Prentice-Hall, Englewood Cliffs (1979)"},{"key":"9972_CR3","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-0957-7","volume-title":"Linear System Theory","author":"FM Callier","year":"1991","unstructured":"Callier, F.M., Desoer, C.A.: Linear System Theory. Springer, Berlin (1991)"},{"issue":"4","key":"9972_CR4","doi-asserted-by":"publisher","first-page":"1239","DOI":"10.1214\/16-BA1017","volume":"11","author":"OA Chkrebtii","year":"2016","unstructured":"Chkrebtii, O.A., Campbell, D.A., Calderhead, B., Girolami, M.A.: Bayesian solution uncertainty quantification for differential equations. Bayesian Anal. 11(4), 1239\u20131267 (2016)","journal-title":"Bayesian Anal."},{"issue":"3","key":"9972_CR5","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1016\/0166-218X(87)90064-3","volume":"16","author":"DS Clark","year":"1987","unstructured":"Clark, D.S.: Short proof of a discrete Gronwall inequality. Discret. Appl. Math. 16(3), 279\u2013281 (1987)","journal-title":"Discret. Appl. Math."},{"issue":"4","key":"9972_CR6","doi-asserted-by":"publisher","first-page":"756","DOI":"10.1137\/17M1139357","volume":"61","author":"J Cockayne","year":"2019","unstructured":"Cockayne, J., Oates, C.J., Sullivan, T.J., Girolami, M.: Bayesian probabilistic numerical methods. SIAM Rev. 61(4), 756\u2013789 (2019)","journal-title":"SIAM Rev."},{"issue":"4","key":"9972_CR7","doi-asserted-by":"publisher","first-page":"1065","DOI":"10.1007\/s11222-016-9671-0","volume":"27","author":"PR Conrad","year":"2017","unstructured":"Conrad, P.R., Girolami, M., S\u00e4rkk\u00e4, S., Stuart, A., Zygalakis, K.: Statistical analysis of differential equations: introducing probability measures on numerical solutions. Stat. Comput. 27(4), 1065\u20131082 (2017)","journal-title":"Stat. Comput."},{"key":"9972_CR8","volume-title":"Introduction to Nonlinear Differential and Integral Equations","author":"HT Davis","year":"1962","unstructured":"Davis, H.T.: Introduction to Nonlinear Differential and Integral Equations. Dover Publications, New York (1962)"},{"issue":"1","key":"9972_CR9","first-page":"163","volume":"IV","author":"P Diaconis","year":"1988","unstructured":"Diaconis, P.: Bayesian numerical analysis. Stat. Decis. Theory Rel. Top. IV(1), 163\u2013175 (1988)","journal-title":"Stat. Decis. Theory Rel. Top."},{"key":"9972_CR10","unstructured":"Gessner, A., Gonzalez, J., Mahsereci, M.: Active multi-information source Bayesian quadrature. In: Uncertainty in Artificial Intelligence (UAI) (2019)"},{"key":"9972_CR11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-12607-3","volume-title":"Solving Ordinary Differential Equations I\u2014Nonstiff Problems","author":"E Hairer","year":"1987","unstructured":"Hairer, E., N\u00f8rsett, S., Wanner, G.: Solving Ordinary Differential Equations I\u2014Nonstiff Problems. Springer, Berlin (1987)"},{"issue":"2179","key":"9972_CR12","first-page":"20150142","volume":"471","author":"P Hennig","year":"2015","unstructured":"Hennig, P., Osborne, M.A., Girolami, M.: Probabilistic numerics and uncertainty in computations. Proc. R. Soc. Lond. A 471(2179), 20150142 (2015)","journal-title":"Proc. R. Soc. Lond. A"},{"key":"9972_CR13","volume-title":"Stochastic Processes and Filtering Theory","author":"A Jazwinski","year":"1970","unstructured":"Jazwinski, A.: Stochastic Processes and Filtering Theory. Academic Press, Cambridge (1970)"},{"key":"9972_CR14","volume-title":"Brownian Motion and Stochastic Calculus","author":"I Karatzas","year":"1991","unstructured":"Karatzas, I., Shreve, S.: Brownian Motion and Stochastic Calculus. Springer, Berlin (1991)"},{"key":"9972_CR15","unstructured":"Kersting, H., Hennig, P.: Active uncertainty calibration in Bayesian ODE solvers. In: Uncertainty in Artificial Intelligence (UAI) (2016)"},{"key":"9972_CR16","unstructured":"Kersting, H., Mahsereci, M.: A Fourier state space model for Bayesian ODE filters. In: Workshop on Invertible Neural Networks, Normalizing Flows, and Explicit Likelihood Models, ICML (2020)"},{"key":"9972_CR17","unstructured":"Kersting, H., Kr\u00e4mer, N., Schiegg, M., Daniel, C., Tiemann, M., Hennig, P.: Differentiable likelihoods for fast inversion of \u2018likelihood-free\u2019 dynamical systems. In: International Conference on Machine Learning (ICML) (2020)"},{"key":"9972_CR18","doi-asserted-by":"crossref","DOI":"10.1093\/oso\/9780198537953.001.0001","volume-title":"Algebraic Riccati Equations","author":"P Lancaster","year":"1995","unstructured":"Lancaster, P., Rodman, L.: Algebraic Riccati Equations. Oxford Science Publications, Oxford (1995)"},{"key":"9972_CR19","doi-asserted-by":"crossref","unstructured":"Law, K., Stuart, A., Zygalakis, K.: Data Assimilation: A Mathematical Introduction, Texts in Applied Mathematics, vol. 62. Springer, Cham (2015)","DOI":"10.1007\/978-3-319-20325-6"},{"issue":"6","key":"9972_CR20","doi-asserted-by":"publisher","first-page":"1265","DOI":"10.1007\/s11222-019-09898-6","volume":"29","author":"HC Lie","year":"2019","unstructured":"Lie, H.C., Stuart, A.M., Sullivan, T.J.: Strong convergence rates of probabilistic integrators for ordinary differential equations. Stat. Comput. 29(6), 1265\u20131283 (2019)","journal-title":"Stat. Comput."},{"key":"9972_CR21","doi-asserted-by":"publisher","first-page":"433","DOI":"10.1137\/0704038","volume":"4","author":"FR Loscalzo","year":"1967","unstructured":"Loscalzo, F.R., Talbot, T.D.: Spline function approximations for solutions of ordinary differential equations. SIAM J. Numer. Anal. 4, 433\u2013445 (1967)","journal-title":"SIAM J. Numer. Anal."},{"key":"9972_CR22","unstructured":"Magnani, E., Kersting, H., Schober, M., Hennig, P.: Bayesian Filtering for ODEs with Bounded Derivatives. arXiv:1709.08471 [csNA] (2017)"},{"key":"9972_CR23","volume-title":"Stochastic Models, Estimation, and Control","author":"PS Maybeck","year":"1979","unstructured":"Maybeck, P.S.: Stochastic Models, Estimation, and Control. Academic Press, Cambridge (1979)"},{"key":"9972_CR24","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1090\/S0025-5718-1962-0136519-5","volume":"16","author":"A Nordsieck","year":"1962","unstructured":"Nordsieck, A.: On numerical integration of ordinary differential equations. Math. Comput. 16, 22\u201349 (1962)","journal-title":"Math. Comput."},{"issue":"6","key":"9972_CR25","doi-asserted-by":"publisher","first-page":"1335","DOI":"10.1007\/s11222-019-09902-z","volume":"29","author":"CJ Oates","year":"2019","unstructured":"Oates, C.J., Sullivan, T.J.: A modern retrospective on probabilistic numerics. Stat. Comput. 29(6), 1335\u20131351 (2019)","journal-title":"Stat. Comput."},{"issue":"3","key":"9972_CR26","doi-asserted-by":"publisher","first-page":"245","DOI":"10.1016\/0378-3758(91)90002-V","volume":"29","author":"A O\u2019Hagan","year":"1991","unstructured":"O\u2019Hagan, A.: Bayes\u2013Hermite quadrature. J. Stat. Plann Inference 29(3), 245\u2013260 (1991)","journal-title":"J. Stat. Plann Inference"},{"key":"9972_CR27","doi-asserted-by":"crossref","unstructured":"O\u2019Hagan, A.: Some Bayesian Numerical Analysis. Bayesian statistics, 4 (Pe\u00f1\u00edscola, 1991), pp. 345\u2013363. Oxford Univ. Press, New York (1992)","DOI":"10.1093\/oso\/9780198522669.003.0019"},{"key":"9972_CR28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-14394-6","volume-title":"Stochastic Differential Equations: An Introduction with Applications","author":"B \u00d8ksendal","year":"2003","unstructured":"\u00d8ksendal, B.: Stochastic Differential Equations: An Introduction with Applications, 5th edn. Springer, Berlin (2003)","edition":"5"},{"key":"9972_CR29","volume-title":"Calcul des probabilit\u00e9s","author":"H Poincar\u00e9","year":"1896","unstructured":"Poincar\u00e9, H.: Calcul des probabilit\u00e9s. Gauthier-Villars, Paris (1896)"},{"key":"9972_CR30","volume-title":"Gaussian Processes for Machine Learning","author":"C Rasmussen","year":"2006","unstructured":"Rasmussen, C., Williams, C.: Gaussian Processes for Machine Learning. MIT Press, London (2006)"},{"key":"9972_CR31","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781107706804","volume-title":"Probabilistic Forecasting and Bayesian Data Assimilation","author":"S Reich","year":"2015","unstructured":"Reich, S., Cotter, C.: Probabilistic Forecasting and Bayesian Data Assimilation. Cambridge University Press, New York (2015)"},{"key":"9972_CR32","doi-asserted-by":"crossref","unstructured":"Ritter, K.: Average-Case Analysis of Numerical Problems. Lecture Notes in Mathematics, vol. 1733. Springer-Verlag, Berlin (2000)","DOI":"10.1007\/BFb0103934"},{"key":"9972_CR33","unstructured":"S\u00e4rkk\u00e4, S.: Recursive Bayesian Inference on Stochastic Differential Equations. PhD thesis, Helsinki University of Technology (2006)"},{"key":"9972_CR34","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781139344203","volume-title":"Bayesian Filtering and Smoothing","author":"S S\u00e4rkk\u00e4","year":"2013","unstructured":"S\u00e4rkk\u00e4, S.: Bayesian Filtering and Smoothing. Cambridge University Press, Cambridge (2013)"},{"key":"9972_CR35","doi-asserted-by":"publisher","DOI":"10.1017\/9781108186735","volume-title":"Applied Stochastic Differential Equations","author":"S S\u00e4rkk\u00e4","year":"2019","unstructured":"S\u00e4rkk\u00e4, S., Solin, A.: Applied Stochastic Differential Equations. Cambridge University Press, Cambridge (2019)"},{"key":"9972_CR36","unstructured":"Schober, M., Duvenaud, D., Hennig, P.: Probabilistic ODE solvers with Runge\u2013Kutta means. In: Advances in Neural Information Processing Systems (NeurIPS) (2014)"},{"issue":"1","key":"9972_CR37","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1007\/s11222-017-9798-7","volume":"29","author":"M Schober","year":"2019","unstructured":"Schober, M., S\u00e4rkk\u00e4, S., Hennig, P.: A probabilistic model for the numerical solution of initial value problems. Stat. Comput. 29(1), 99\u2013122 (2019)","journal-title":"Stat. Comput."},{"key":"9972_CR38","doi-asserted-by":"crossref","unstructured":"Skilling, J.: Bayesian solutions of ordinary differential equations. Maximum Entropy and Bayesian Methods, Seattle (1991)","DOI":"10.1007\/978-94-017-2219-3_2"},{"key":"9972_CR39","unstructured":"Solak, E., Murray-Smith, R., Leithead, W.E., Leith, D.J., Rasmussen, C.E.: Derivative observations in Gaussian process models of dynamic systems. In: Advances in Neural Information Processing Systems (NeurIPS) (2003)"},{"key":"9972_CR40","doi-asserted-by":"publisher","DOI":"10.1090\/gsm\/140","volume-title":"Ordinary Differential Equations and Dynamical Systems","author":"G Teschl","year":"2012","unstructured":"Teschl, G.: Ordinary Differential Equations and Dynamical Systems. American Mathematical Society, Providence (2012)"},{"key":"9972_CR41","unstructured":"Teymur, O., Zygalakis, K., Calderhead, B.: Probabilistic linear multistep methods. In: Sugiyama, M., Luxburg, U.V., Guyon, I., Garnett, R., Lee, D.D. (eds.) Advances in Neural Information Processing Systems (NeurIPS), pp. 4314\u20134321. Curran Associates Inc (2016)"},{"key":"9972_CR42","unstructured":"Teymur, O., Lie, H.C., Sullivan, T.J., Calderhead, B.: Implicit probabilistic integrators for ODEs. In: Advances in Neural Information Processing Systems (NeurIPS) (2018)"},{"issue":"6","key":"9972_CR43","doi-asserted-by":"publisher","first-page":"1297","DOI":"10.1007\/s11222-019-09900-1","volume":"29","author":"F Tronarp","year":"2019","unstructured":"Tronarp, F., Kersting, H., S\u00e4rkk\u00e4, S., Hennig, P.: Probabilistic solutions to ordinary differential equations as nonlinear Bayesian filtering: a new perspective. Stat. Comput. 29(6), 1297\u20131315 (2019)","journal-title":"Stat. Comput."},{"key":"9972_CR44","doi-asserted-by":"crossref","unstructured":"Tronarp, F., Kersting, H., S\u00e4rkk\u00e4, S., Hennig, P.: Bayesian ode solvers: The maximum a posteriori estimate. arXiv:2004.00623 [mathNA] (2020)","DOI":"10.1007\/s11222-021-09993-7"},{"key":"9972_CR45","unstructured":"Wang J, Cockayne, J., Oates, C.: On the Bayesian solution of differential equations. In: Proceedings of the 38th International Workshop on Bayesian Inference and Maximum Entropy Methods in Science and Engineering (2018)"},{"key":"9972_CR46","unstructured":"Xiaoyue, X., Briol, F.X., Girolami, M.: Bayesian quadrature for multiple related integrals. In: International Conference on Machine Learning (ICML) (2018)"}],"container-title":["Statistics and Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11222-020-09972-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11222-020-09972-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11222-020-09972-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,13]],"date-time":"2024-08-13T18:09:21Z","timestamp":1723572561000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11222-020-09972-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,9,12]]},"references-count":46,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2020,11]]}},"alternative-id":["9972"],"URL":"https:\/\/doi.org\/10.1007\/s11222-020-09972-4","relation":{},"ISSN":["0960-3174","1573-1375"],"issn-type":[{"value":"0960-3174","type":"print"},{"value":"1573-1375","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,9,12]]},"assertion":[{"value":"20 March 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 August 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 September 2020","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Compliance with ethical standards"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}