{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T20:32:53Z","timestamp":1777321973360,"version":"3.51.4"},"reference-count":55,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2025,2,4]],"date-time":"2025-02-04T00:00:00Z","timestamp":1738627200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,2,4]],"date-time":"2025-02-04T00:00:00Z","timestamp":1738627200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Found Comput Math"],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1007\/s10208-025-09689-8","type":"journal-article","created":{"date-parts":[[2025,2,4]],"date-time":"2025-02-04T16:14:50Z","timestamp":1738685690000},"page":"999-1068","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Safely Learning Dynamical Systems"],"prefix":"10.1007","volume":"26","author":[{"given":"Amir Ali","family":"Ahmadi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abraar","family":"Chaudhry","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vikas","family":"Sindhwani","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stephen","family":"Tu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,2,4]]},"reference":[{"key":"9689_CR1","doi-asserted-by":"crossref","unstructured":"Aharon Ben-Tal and Arkadi Nemirovski. Lectures on Modern Convex Optimization. Society for Industrial and Applied Mathematics, 2001.","DOI":"10.1137\/1.9780898718829"},{"issue":"1","key":"9689_CR2","doi-asserted-by":"publisher","first-page":"399","DOI":"10.1137\/18M1172843","volume":"29","author":"Amir Ali Ahmadi","year":"2019","unstructured":"Amir\u00a0Ali Ahmadi, Etienne de\u00a0Klerk, and Georgina Hall. 2019. Polynomial norms. SIAM Journal on Optimization, 29(1):399\u2013422,","journal-title":"SIAM Journal on Optimization"},{"key":"9689_CR3","doi-asserted-by":"crossref","unstructured":"Ainesh Bakshi, Allen Liu, Ankur Moitra, and Morris Yau. A new approach to learning linear dynamical systems. In Proceedings of the 55th Annual ACM Symposium on Theory of Computing, page 335\u2013348. Association for Computing Machinery, 2023.","DOI":"10.1145\/3564246.3585247"},{"key":"9689_CR4","unstructured":"Alessandro Luppi, Andrea Bisoffi, Claudio De\u00a0Persis, and Pietro Tesi. Data-driven design of safe control for polynomial systems. arXiv:2112.12664, 2021."},{"issue":"1","key":"9689_CR5","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1137\/20M1388644","volume":"65","author":"Amir Ali Ahmadi and Bachir El Khadir","year":"2023","unstructured":"Amir\u00a0Ali Ahmadi and Bachir El\u00a0Khadir. Learning dynamical systems with side information. SIAM Review, 65(1):183\u2013223, 2023.","journal-title":"SIAM Review"},{"key":"9689_CR6","unstructured":"Amir\u00a0Ali Ahmadi and Oktay G\u00fcnl\u00fck. Robust-to-dynamics optimization. To appear in Mathematics of Operations Research, 2024. Available at arXiv:1805.03682."},{"key":"9689_CR7","unstructured":"Amir\u00a0Ali Ahmadi, Abraar Chaudhry, Vikas Sindhwani, and Stephen Tu. Safely learning dynamical systems from short trajectories. In Proceedings of the 3rd Conference on Learning for Dynamics and Control, volume 144 of Proceedings of Machine Learning Research, pages 498\u2013509. PMLR, 2021."},{"key":"9689_CR8","doi-asserted-by":"crossref","unstructured":"Anayo\u00a0K. Akametalu, Jaime\u00a0F. Fisac, Jeremy\u00a0H. Gillula, Shahab Kaynama, Melanie\u00a0N. Zeilinger, and Claire\u00a0J. Tomlin. Reachability-based safe learning with Gaussian processes. In 53rd IEEE Conference on Decision and Control, 2014.","DOI":"10.1109\/CDC.2014.7039601"},{"key":"9689_CR9","doi-asserted-by":"crossref","unstructured":"Andrea Bisoffi, Claudio De Persis, and Pietro Tesi. Data-driven control via Petersen\u2019s lemma. Automatica, 145:110537, 2022. ISSN 0005-1098.","DOI":"10.1016\/j.automatica.2022.110537"},{"key":"9689_CR10","unstructured":"Andrew Taylor, Andrew Singletary, Yisong Yue, and Aaron Ames. Learning for safety-critical control with control barrier functions. In Proceedings of the 2nd Conference on Learning for Dynamics and Control, 2020."},{"issue":"2","key":"9689_CR11","doi-asserted-by":"publisher","first-page":"520","DOI":"10.1016\/j.automatica.2007.06.013","volume":"44","author":"Zvi Artstein","year":"2008","unstructured":"Zvi Artstein and Sa\u0161a\u00a0V. Rakovi\u0107. Feedback and invariance under uncertainty via set-iterates. Automatica, 44(2):520\u2013525, 2008.","journal-title":"Automatica"},{"key":"9689_CR12","doi-asserted-by":"crossref","unstructured":"Athanasios\u00a0C. Antoulas. Approximation of Large-Scale Dynamical Systems. Society for Industrial and Applied Mathematics, 2005.","DOI":"10.1137\/1.9780898718713"},{"key":"9689_CR13","unstructured":"G.\u00a0Birkhoff. Tres Observaciones Sobre el Algebra Lineal. Univ. Nac. Tucuman, Ser. A, 5:147\u2013154, 1946."},{"issue":"11","key":"9689_CR14","doi-asserted-by":"publisher","first-page":"1747","DOI":"10.1016\/S0005-1098(99)00113-2","volume":"35","author":"Franco Blanchini","year":"1999","unstructured":"Franco Blanchini. Set invariance in control. Automatica, 35(11):1747\u20131767, 1999.","journal-title":"Automatica"},{"key":"9689_CR15","doi-asserted-by":"crossref","unstructured":"Carsten\u00a0W. Scherer and Camile W.\u00a0J. Hol. Matrix sum-of-squares relaxations for robust semi-definite programs. Math. Program., 107(1\u20132):189\u2013211, 2006.","DOI":"10.1007\/s10107-005-0684-2"},{"key":"9689_CR16","unstructured":"Daniel\u00a0Ammon Dowler. Bounding the norm of matrix powers. In BYU ScholarsArchive, 2013."},{"issue":"1","key":"9689_CR17","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1214\/18-AOS1683","volume":"47","author":"Yohann De Castro","year":"2019","unstructured":"Yohann De\u00a0Castro, Fabrice Gamboa, Didier Henrion, Roxana Hess, and Jean-Bernard Lasserre. Approximate optimal designs for multivariate polynomial regression. Ann. Statist., 47(1):127\u2013155, 2019.","journal-title":"Ann. Statist."},{"key":"9689_CR18","doi-asserted-by":"crossref","unstructured":"Felix Berkenkamp and Angela\u00a0P. Schoellig. Safe and robust learning control with Gaussian processes. In 2015 European Control Conference (ECC), 2015.","DOI":"10.1109\/ECC.2015.7330913"},{"key":"9689_CR19","unstructured":"Felix Berkenkamp, Matteo Turchetta, Angela\u00a0P. Schoellig, and Andreas Krause. Safe model-based reinforcement learning with stability guarantees. In Neural Information Processing Systems, 2017."},{"key":"9689_CR20","doi-asserted-by":"crossref","unstructured":"Friedrich Pukelsheim. Optimal Design of Experiments. Society for Industrial and Applied Mathematics, 2006.","DOI":"10.1137\/1.9780898719109"},{"key":"9689_CR21","unstructured":"Gerald\u00a0B. Folland. Real Analysis: Modern Techniques and Their Applications. Wiley, 1999."},{"key":"9689_CR22","doi-asserted-by":"crossref","unstructured":"Grigoriy Blekherman, Pablo\u00a0A. Parrilo, and Rekha Thomas. Semidefinite Optimization and Convex Algebraic Geometry. SIAM Series on Optimization, 2013.","DOI":"10.1137\/1.9781611972290"},{"issue":"8","key":"9689_CR23","doi-asserted-by":"publisher","first-page":"4210","DOI":"10.1109\/TAC.2021.3115436","volume":"67","author":"Meichen Guo","year":"2022","unstructured":"Meichen Guo, Claudio De\u00a0Persis, and Pietro Tesi. Data-driven stabilization of nonlinear polynomial systems with noisy data. IEEE Transactions on Automatic Control, 67(8):4210\u20134217, 2022.","journal-title":"IEEE Transactions on Automatic Control"},{"key":"9689_CR24","unstructured":"Homanga Bharadhwaj, Aviral Kumar, Nicholas Rhinehart, Sergey Levine, Florian Shkurti, and Animesh Garg. Conservative safety critics for exploration. In International Conference on Learning Representations, 2021."},{"key":"9689_CR25","doi-asserted-by":"crossref","unstructured":"Jared Miller and Mario Sznaier. Bounding the Distance to Unsafe Sets with Convex Optimization. IEEE Transactions on Automatic Control, 2023.","DOI":"10.1109\/TAC.2023.3285862"},{"key":"9689_CR26","doi-asserted-by":"crossref","unstructured":"Jean\u00a0Bernard Lasserre. Moments, Positive Polynomials And Their Applications, volume\u00a01. World Scientific, 2010.","DOI":"10.1142\/p665"},{"key":"9689_CR27","doi-asserted-by":"crossref","unstructured":"Jean-Baptiste Hiriart-Urruty and Hai\u00a0Yen Le. Convexifying the set of matrices of bounded rank: applications to the quasiconvexification and convexification of the rank function. Optimization Letters, 6(5):841\u2013849, 2012.","DOI":"10.1007\/s11590-011-0304-4"},{"key":"9689_CR28","unstructured":"Jesse Zhang, Brian Cheung, Chelsea Finn, Sergey Levine, and Dinesh Jayaraman. Cautious adaptation for reinforcement learning in safety-critical settings. In Proceedings of the 37th International Conference on Machine Learning, Proceedings of Machine Learning Research, 2020."},{"key":"9689_CR29","doi-asserted-by":"crossref","unstructured":"Karel\u00a0J. Keesman. System Identification: An Introduction, volume\u00a02. Springer, 2011.","DOI":"10.1007\/978-0-85729-522-4"},{"issue":"2","key":"9689_CR30","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1016\/0005-1098(71)90059-8","volume":"7","author":"Karl Johan \u00c5str\u00f6m and Peter Eykhoff","year":"1971","unstructured":"Karl\u00a0Johan \u00c5str\u00f6m and Peter Eykhoff. System identification-a survey. Automatica, 7(2):123\u2013162, 1971.","journal-title":"Automatica"},{"key":"9689_CR31","doi-asserted-by":"crossref","unstructured":"Kim\u00a0Peter Wabersich and Melanie\u00a0N. Zeilinger. A predictive safety filter for learning-based control of constrained nonlinear dynamical systems. Automatica, 129:109597, 2021.","DOI":"10.1016\/j.automatica.2021.109597"},{"issue":"5","key":"9689_CR32","doi-asserted-by":"publisher","first-page":"2944","DOI":"10.1137\/130914565","volume":"52","author":"Milan Korda","year":"2014","unstructured":"Milan Korda, Didier Henrion, and Colin\u00a0N. Jones. Convex computation of the maximum controlled invariant set for polynomial control systems. SIAM Journal on Control and Optimization, 52(5):2944\u20132969, 2014.","journal-title":"SIAM Journal on Control and Optimization"},{"key":"9689_CR33","doi-asserted-by":"crossref","unstructured":"L.\u00a0Lov\u00e1sz. Semidefinite Programs and Combinatorial Optimization, pages 137\u2013194. Springer, 2003.","DOI":"10.1007\/0-387-22444-0_6"},{"key":"9689_CR34","doi-asserted-by":"crossref","unstructured":"Lukas Brunke, Melissa Greeff, Adam\u00a0W. Hall, Zhaocong Yuan, Siqi Zhou, Jacopo Panerati, and Angela\u00a0P. Schoellig. Safe learning in robotics: From learning-based control to safe reinforcement learning. Annual Reviews of Control, Robotics, and Autonomous Systems, 2021.","DOI":"10.1146\/annurev-control-042920-020211"},{"issue":"4","key":"9689_CR35","doi-asserted-by":"publisher","first-page":"1069","DOI":"10.1109\/TNNLS.2017.2654539","volume":"29","author":"Tommaso Mannucci","year":"2018","unstructured":"Tommaso Mannucci, Erik-Jan van Kampen, Cornelis de\u00a0Visser, and Qiping Chu. Safe exploration algorithms for reinforcement learning controllers. IEEE Transactions on Neural Networks and Learning Systems, 29(4):1069\u20131081, 2018.","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"9689_CR36","doi-asserted-by":"crossref","unstructured":"Miguel\u00a0Sousa Lobo, Lieven Vandenberghe, Stephen Boyd, and Herv\u00c3\u00a9 Lebret. Applications of second-order cone programming. Linear Algebra and its Applications, 284(1):193\u2013228, 1998.","DOI":"10.1016\/S0024-3795(98)10032-0"},{"key":"9689_CR37","doi-asserted-by":"crossref","unstructured":"Monique Laurent. Sums of Squares, Moment Matrices and Optimization Over Polynomials, pages 157\u2013270. Springer New York, New York, NY, 2009. ISBN 978-0-387-09686-5.","DOI":"10.1007\/978-0-387-09686-5_7"},{"key":"9689_CR38","first-page":"551","volume":"24","author":"Mitio Nagumo","year":"1942","unstructured":"Mitio Nagumo. \u00dcber die Lage der Integralkurven gew\u00f6hnlicher Differentialgleichungen. Proceedings of the Physico-Mathematical Society of Japan., 24:551\u2013559, 1942.","journal-title":"Proceedings of the Physico-Mathematical Society of Japan."},{"key":"9689_CR39","unstructured":"Pablo Parrilo. Structured semidefinite programs and semialgebraic geometry methods in robustness and optimization. PhD thesis, California Institute of Technology, 2000."},{"key":"9689_CR40","doi-asserted-by":"crossref","unstructured":"Paul\u00a0C. Bell, Jean-Charles Delvenne, Rapha\u00ebl\u00a0M. Jungers, and Vincent\u00a0D. Blondel. The continuous skolem-pisot problem. Theoretical Computer Science, 411(40):3625\u20133634, 2010. ISSN 0304-3975.","DOI":"10.1016\/j.tcs.2010.06.005"},{"issue":"3","key":"9689_CR41","doi-asserted-by":"publisher","first-page":"371","DOI":"10.1137\/S003614450444614X","volume":"49","author":"Imre P\u00f3lik","year":"2007","unstructured":"Imre P\u00f3lik and Tam\u00e1s Terlaky. A survey of the S-lemma. SIAM Review, 49(3):371\u2013418, 2007.","journal-title":"SIAM Review"},{"issue":"3","key":"9689_CR42","doi-asserted-by":"publisher","first-page":"969","DOI":"10.1512\/iumj.1993.42.42045","volume":"42","author":"Mihai Putinar","year":"1993","unstructured":"Mihai Putinar. Positive polynomials on compact semi-algebraic sets. Indiana University Mathematics Journal, 42(3):969\u2013984, 1993.","journal-title":"Indiana University Mathematics Journal"},{"key":"9689_CR43","doi-asserted-by":"crossref","unstructured":"Richard Cheng, G\u00e1bor Orosz, Richard\u00a0M. Murray, and Joel\u00a0W. Burdick. End-to-end safe reinforcement learning through barrier functions for safety-critical continuous control tasks. In Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence and Thirty-First Innovative Applications of Artificial Intelligence Conference and Ninth AAAI Symposium on Educational Advances in Artificial Intelligence, 2019.","DOI":"10.1609\/aaai.v33i01.33013387"},{"key":"9689_CR44","doi-asserted-by":"crossref","unstructured":"Sarah Dean, Horia Mania, Nikolai Matni, Benjamin Recht, and Stephen Tu. On the sample complexity of the linear quadratic regulator. Foundations of Computational Mathematics, 20(4):633\u2013679, 2020. ISSN 1615-3383.","DOI":"10.1007\/s10208-019-09426-y"},{"key":"9689_CR45","doi-asserted-by":"crossref","unstructured":"Sarah Dean, Stephen Tu, Nikolai Matni, and Benjamin Recht. Safely learning to control the constrained linear quadratic regulator. In Proceedings of the American Control Conference, 2019.","DOI":"10.23919\/ACC.2019.8814865"},{"key":"9689_CR46","unstructured":"Shaoru Chen, Nikolai Matni, Manfred Morari, and Victor\u00a0M. Preciado. System level synthesis-based robust model predictive control through convex inner approximation. arXiv:2111.05509, 2021."},{"key":"9689_CR47","doi-asserted-by":"crossref","unstructured":"Shaoru Chen, Victor\u00a0M. Preciado, Manfred Morari, and Nikolai Matni. Robust model predictive control with polytopic model uncertainty through system level synthesis. arXiv:2203.11375, 2022.","DOI":"10.1109\/CDC51059.2022.9992666"},{"key":"9689_CR48","unstructured":"Stanislaw\u00a0H. \u017bak. Systems and Control. Oxford Series in Electrical and Computer Engineering. Oxford University Press, 2003."},{"key":"9689_CR49","unstructured":"Steffen W.\u00a0R. Werner and Benjamin Peherstorfer. On the sample complexity of stabilizing linear dynamical systems from data. Foundations of Computational Mathematics, 2023. ISSN 1615-3383."},{"key":"9689_CR50","doi-asserted-by":"crossref","unstructured":"Stephen Boyd, Laurent El\u00a0Ghaoui, Eric Feron, and Venkataramanan Balakrishnan. Linear Matrix Inequalities In System And Control Theory. SIAM, 1994.","DOI":"10.1137\/1.9781611970777"},{"key":"9689_CR51","doi-asserted-by":"crossref","unstructured":"Steven\u00a0L. Brunton and J.\u00a0Nathan Kutz. Data-Driven Science and Engineering: Machine learning, Dynamical Systems, and Control. Cambridge University Press, 2019.","DOI":"10.1017\/9781108380690"},{"key":"9689_CR52","doi-asserted-by":"crossref","unstructured":"Thomas Gurriet, Mark Mote, Andrew Singletary, Eric Feron, and Aaron\u00a0D. Ames. A scalable controlled set invariance framework with practical safety guarantees. In Proceedings of the 58th IEEE Conference on Decision and Control, 2019.","DOI":"10.1109\/CDC40024.2019.9030159"},{"key":"9689_CR53","doi-asserted-by":"crossref","unstructured":"Torsten Koller, Felix Berkenkamp, Matteo Turchetta, Joschka Boedecker, and Andreas Krause. Learning-based model predictive control for safe exploration and reinforcement learning. arXiv:1906.12189, 2019.","DOI":"10.1109\/CDC.2018.8619572"},{"key":"9689_CR54","unstructured":"Tyler Lu, Martin Zinkevich, Craig Boutilier, Binz Roy, and Dale Schuurmans. Safe exploration for identifying linear systems via robust optimization. arXiv:1711.11165, 2017."},{"key":"9689_CR55","unstructured":"Wenhao Luo, Wen Sun, and Ashish Kapoor. No-regret safe learning for online nonlinear control with control barrier functions. In ICRA Workshop on Safe Robot Control with Learned Motion and Environment Models, 2021."}],"container-title":["Foundations of Computational Mathematics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10208-025-09689-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10208-025-09689-8","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10208-025-09689-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T19:37:22Z","timestamp":1777318642000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10208-025-09689-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,4]]},"references-count":55,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,4]]}},"alternative-id":["9689"],"URL":"https:\/\/doi.org\/10.1007\/s10208-025-09689-8","relation":{},"ISSN":["1615-3375","1615-3383"],"issn-type":[{"value":"1615-3375","type":"print"},{"value":"1615-3383","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2,4]]},"assertion":[{"value":"28 June 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 June 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 October 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 February 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}