{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T01:37:25Z","timestamp":1760060245162,"version":"build-2065373602"},"reference-count":60,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2025,8,19]],"date-time":"2025-08-19T00:00:00Z","timestamp":1755561600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Entropy"],"abstract":"<jats:p>Neural ordinary differential equations (neural ODEs) are a well-established tool for optimizing the parameters of dynamical systems, with applications in image classification, optimal control, and physics learning. Although dynamical systems of interest often evolve on Lie groups and more general differentiable manifolds, theoretical results for neural ODEs are frequently phrased on Rn. We collect recent results for neural ODEs on manifolds and present a unifying derivation of various results that serves as a tutorial to extend existing methods to differentiable manifolds. We also extend the results to the recent class of neural ODEs on Lie groups, highlighting a non-trivial extension of manifold neural ODEs that exploits the Lie group structure.<\/jats:p>","DOI":"10.3390\/e27080878","type":"journal-article","created":{"date-parts":[[2025,8,19]],"date-time":"2025-08-19T15:29:29Z","timestamp":1755617369000},"page":"878","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Geometric Neural Ordinary Differential Equations: From Manifolds to Lie Groups"],"prefix":"10.3390","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3002-4479","authenticated-orcid":false,"given":"Yannik P.","family":"Wotte","sequence":"first","affiliation":[{"name":"Robotics and Mechatronics, EEMCS, University of Twente (UT), Drienerlolaan 5, 7522 NB Enschede, The Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8693-0900","authenticated-orcid":false,"given":"Federico","family":"Califano","sequence":"additional","affiliation":[{"name":"Robotics and Mechatronics, EEMCS, University of Twente (UT), Drienerlolaan 5, 7522 NB Enschede, The Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8212-7387","authenticated-orcid":false,"given":"Stefano","family":"Stramigioli","sequence":"additional","affiliation":[{"name":"Robotics and Mechatronics, EEMCS, University of Twente (UT), Drienerlolaan 5, 7522 NB Enschede, The Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,8,19]]},"reference":[{"key":"ref_1","unstructured":"Chen, R.T.Q., Rubanova, Y., Bettencourt, J., and Duvenaud, D. (2018, January 3\u20138). Neural Ordinary Differential Equations. Proceedings of the 32nd Conference on Neural Information Processing Systems (NeurIPS 2018), Montreal, QC, Canada. Available online: http:\/\/arxiv.org\/abs\/1806.07366."},{"key":"ref_2","first-page":"3952","article-title":"Dissecting neural ODEs","volume":"2020","author":"Massaroli","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"5855","DOI":"10.1016\/j.ifacol.2023.10.079","article-title":"Physically Consistent Neural ODEs for Learning Multi-Physics Systems","volume":"56","author":"Zakwan","year":"2023","journal-title":"IFAC-PapersOnLine"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Sholokhov, A., Liu, Y., Mansour, H., and Nabi, S. (2023). Physics-informed neural ODE (PINODE): Embedding physics into models using collocation points. Sci. Rep., 13.","DOI":"10.1038\/s41598-023-36799-6"},{"key":"ref_5","unstructured":"Ghanem, P., Demirkaya, A., Imbiriba, T., Ramezani, A., Danziger, Z., and Erdogmus, D. (2024). Learning Physics Informed Neural ODEs with Partial Measurements. Proc. AAAI Conf. Artif. Intell., AAAI-25, Available online: http:\/\/arxiv.org\/abs\/2412.08681."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"2126","DOI":"10.1137\/21M1414279","article-title":"Optimal Energy Shaping via Neural Approximators","volume":"21","author":"Massaroli","year":"2022","journal-title":"SIAM J. Appl. Dyn. Syst."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"236","DOI":"10.1007\/s10462-024-10894-0","article-title":"On the applications of neural ordinary differential equations in medical image analysis","volume":"57","author":"Niu","year":"2024","journal-title":"Artif. Intell. Rev."},{"key":"ref_8","unstructured":"Oh, Y., Kam, S., Lee, J., Lim, D.Y., Kim, S., and Bui, A.A.T. (2025). Comprehensive Review of Neural Differential Equations for Time Series Analysis. arXiv, Available online: http:\/\/arxiv.org\/abs\/2502.09885."},{"key":"ref_9","unstructured":"Poli, M., Massaroli, S., Scimeca, L., Chun, S., Oh, S.J., Yamashita, A., Asama, H., Park, J., and Garg, A. (2021, January 6\u201314). Neural Hybrid Automata: Learning Dynamics with Multiple Modes and Stochastic Transitions. Proceedings of the 35th Conference on Neural Information Processing Systems (NeurIPS 2021), Online. Available online: http:\/\/arxiv.org\/abs\/2106.04165."},{"key":"ref_10","unstructured":"Chen, R.T.Q., Amos, B., and Nickel, M. (2021, January 3\u20137). Learning Neural Event Functions for Ordinary Differential Equations. Proceedings of the Ninth International Conference on Learning Representations (ICLR 2021), Virtual. Available online: http:\/\/arxiv.org\/abs\/2011.03902."},{"key":"ref_11","unstructured":"Davis, J.Q., Choromanski, K., Varley, J., Lee, H., Slotine, J.J., Likhosterov, V., Weller, A., Makadia, A., and Sindhwani, V. (2020). Time Dependence in Non-Autonomous Neural ODEs. arXiv, Available online: http:\/\/arxiv.org\/abs\/2005.01906."},{"key":"ref_12","unstructured":"Dupont, E., Doucet, A., and Teh, Y.W. (2019, January 8\u201314). Augmented Neural ODEs. Proceedings of the 33rd International Conference on Neural Information Processing Systems (NeurIPS 2019), Vancouver, BC, Canada. Available online: http:\/\/arxiv.org\/abs\/1904.01681."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Chu, H., Miyatake, Y., Cui, W., Wei, S., and Furihata, D. (2024, January 3\u20139). Structure-Preserving Physics-Informed Neural Networks with Energy or Lyapunov Structure. Proceedings of the 33rd International Joint Conference on Artificial Intelligence (IJCAI 24), Jeju, Republic of Korea.","DOI":"10.24963\/ijcai.2024\/428"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"102577","DOI":"10.1016\/j.jocs.2025.102577","article-title":"Energy dissipation preserving physics informed neural network for Allen\u2013Cahn equations","volume":"87","year":"2025","journal-title":"J. Comput. Sci."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1016\/S0005-1098(98)00119-8","article-title":"Tracking for fully actuated mechanical systems: A geometric framework","volume":"35","author":"Bullo","year":"1999","journal-title":"Automatica"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Marsden, J.E., and Ratiu, T.S. (1999). Introduction to Mechanics and Symmetry, Springer.","DOI":"10.1007\/978-0-387-21792-5"},{"key":"ref_17","unstructured":"Whiteley, N., Gray, A., and Rubin-Delanchy, P. (2025). Statistical exploration of the Manifold Hypothesis. arXiv, Available online: http:\/\/arxiv.org\/abs\/2208.11665."},{"key":"ref_18","unstructured":"Lou, A., Lim, D., Katsman, I., Huang, L., Jiang, Q., Lim, S.N., and De Sa, C. (2020, January 6\u201312). Neural Manifold Ordinary Differential Equations. Proceedings of the 34th Conference on Neural Information Processing Systems (NeurIPS 2020), Online. Available online: http:\/\/arxiv.org\/abs\/2006.10254."},{"key":"ref_19","unstructured":"Falorsi, L., and Forr\u00e9, P. (2020). Neural Ordinary Differential Equations on Manifolds. arXiv, Available online: http:\/\/arxiv.org\/abs\/2006.06663."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"3695","DOI":"10.1109\/TRO.2024.3428433","article-title":"Port-Hamiltonian Neural ODE Networks on Lie Groups for Robot Dynamics Learning and Control","volume":"40","author":"Duong","year":"2024","journal-title":"IEEE Trans. Robot."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"2221","DOI":"10.1177\/02783649241256044","article-title":"Optimal potential shaping on SE(3) via neural ordinary differential equations on Lie groups","volume":"43","author":"Wotte","year":"2024","journal-title":"Int. J. Robot. Res."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"1113","DOI":"10.1038\/s42256-022-00575-4","article-title":"Data-driven discovery of intrinsic dynamics","volume":"4","author":"Floryan","year":"2022","journal-title":"Nat. Mach. Intell."},{"key":"ref_23","unstructured":"Andersdotter, E., Persson, D., and Ohlsson, F. (2024). Equivariant Manifold Neural ODEs and Differential Invariants. arXiv, Available online: http:\/\/arxiv.org\/abs\/2401.14131."},{"key":"ref_24","unstructured":"Wotte, Y.P. (2021). Optimal Potential Shaping on SE(3) via Neural Approximators. [Master\u2019s Thesis, University of Twente]."},{"key":"ref_25","unstructured":"Kidger, P. (2022). On Neural Differential Equations. [Ph.D. Thesis, Mathematical Institute, University of Oxford]."},{"key":"ref_26","unstructured":"Gholami, A., Keutzer, K., and Biros, G. (2019, January 10\u201316). ANODE: Unconditionally Accurate Memory-Efficient Gradients for Neural ODEs. Proceedings of the 28th International Joint Conference on Artificial Intelligence (IJCAI 19), Macao. Available online: http:\/\/arxiv.org\/abs\/1902.10298."},{"key":"ref_27","unstructured":"Kidger, P., Morrill, J., Foster, J., and Lyons, T.J. (2020, January 6\u201312). Neural Controlled Differential Equations for Irregular Time Series. Proceedings of the 34th Conference on Neural Information Processing Systems (NeurIPS 2020), Online. Available online: http:\/\/arxiv.org\/abs\/2005.08926."},{"key":"ref_28","unstructured":"Li, X., Wong, T.L., Chen, R.T.Q., and Duvenaud, D. (2020, January 26\u201328). Scalable Gradients for Stochastic Differential Equations. Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics (AISTATS 2020), Online. Available online: http:\/\/arxiv.org\/abs\/2001.01328."},{"key":"ref_29","unstructured":"Liu, Y., Cheng, J., Zhao, H., Xu, T., Zhao, P., Tsung, F., Li, J., and Rong, Y. (2024, January 7\u201311). SEGNO: Generalizing Equivariant Graph Neural Networks with Physical Inductive Biases. Proceedings of the 12th International Conference on Learning Representations (ICLR 2024), Vienna, Austria. Available online: http:\/\/arxiv.org\/abs\/2308.13212."},{"key":"ref_30","unstructured":"Greydanus, S., Dzamba, M., and Yosinski, J. (2019, January 8\u201314). Hamiltonian Neural Networks. Proceedings of the 33rd Conference on Neural Information Processing Systems (NeurIPS 2019), Vancouver, BC, Canada. Available online: http:\/\/arxiv.org\/abs\/1906.01563."},{"key":"ref_31","unstructured":"Finzi, M., Wang, K.A., and Wilson, A.G. (2020, January 6\u201312). Simplifying Hamiltonian and Lagrangian Neural Networks via Explicit Constraints. Proceedings of the 34th Conference on Neural Information Processing Systems (NeurIPS 2020), Online. Available online: http:\/\/arxiv.org\/abs\/2010.13581."},{"key":"ref_32","unstructured":"Cranmer, M., Greydanus, S., Hoyer, S., Research, G., Battaglia, P., Spergel, D., and Ho, S. (2020, January 26). Lagrangian Neural Networks. Proceedings of the ICLR 2020 Deep Differential Equations Workshop, Addis Ababa, Ethiopia. Available online: http:\/\/arxiv.org\/abs\/2003.04630."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"015003","DOI":"10.1088\/2632-2153\/acb03e","article-title":"Learning the Dynamics of Particle-based Systems with Lagrangian Graph Neural Networks","volume":"4","author":"Bhattoo","year":"2023","journal-title":"Mach. Learn. Sci. Technol."},{"key":"ref_34","unstructured":"Xiao, S., Zhang, J., and Tang, Y. (2024). Generalized Lagrangian Neural Networks. arXiv, Available online: http:\/\/arxiv.org\/abs\/2401.03728."},{"key":"ref_35","unstructured":"Rettberg, J., Kneifl, J., Herb, J., Buchfink, P., Fehr, J., and Haasdonk, B. (2024). Data-Driven Identification of Latent Port-Hamiltonian Systems. arXiv, 37\u201399. Available online: http:\/\/arxiv.org\/abs\/2408.08185."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Duong, T., and Atanasov, N. (2021, January 12\u201316). Hamiltonian-based Neural ODE Networks on the SE(3) Manifold For Dynamics Learning and Control. Proceedings of the Robotics: Science and Systems (RSS 2021), Online. Available online: http:\/\/arxiv.org\/abs\/2106.12782v3.","DOI":"10.15607\/RSS.2021.XVII.086"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"33154","DOI":"10.1063\/5.0251475","article-title":"Training stiff neural ordinary differential equations with explicit exponential integration methods","volume":"35","author":"Fronk","year":"2025","journal-title":"Chaos"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"388","DOI":"10.1007\/978-3-031-44201-8_32","article-title":"S-SOLVER: Numerically Stable Adaptive Step Size Solver for Neural ODEs","volume":"Volume 14262","author":"Kloberdanz","year":"2023","journal-title":"Artificial Neural Networks and Machine Learning\u2014ICANN 2023"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"318","DOI":"10.1007\/s42979-025-03832-6","article-title":"On Tuning Neural ODE for Stability, Consistency and Faster Convergence","volume":"6","author":"Akhtar","year":"2025","journal-title":"SN Comput. Sci."},{"key":"ref_40","first-page":"27527","article-title":"On Numerical Integration in Neural Ordinary Differential Equations","volume":"Volume 162","author":"Zhu","year":"2022","journal-title":"Proceedings of the 39th International Conference on Machine Learning (ICML 2022)"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1016\/S0168-9274(98)00030-0","article-title":"High order Runge-Kutta methods on manifolds","volume":"29","year":"1999","journal-title":"Appl. Numer. Math."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"1040","DOI":"10.1016\/j.jcp.2012.12.031","article-title":"An introduction to Lie group integrators\u2014Basics, New Developments and Applications","volume":"257","author":"Celledoni","year":"2014","journal-title":"J. Comput. Phys."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Ma, Y., Dixit, V., Innes, M.J., Guo, X., and Rackauckas, C. (2021, January 20\u201324). A Comparison of Automatic Differentiation and Continuous Sensitivity Analysis for Derivatives of Differential Equation Solutions. Proceedings of the 2021 IEEE High Performance Extreme Computing Conference (HPEC 2021), Online.","DOI":"10.1109\/HPEC49654.2021.9622796"},{"key":"ref_44","unstructured":"Saemundsson, S., Terenin, A., Hofmann, K., and Deisenroth, M.P. (2020, January 26\u201328). Variational Integrator Networks for Physically Structured Embeddings. Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics (AISTATS 2020), Online. Available online: http:\/\/arxiv.org\/abs\/1910.09349."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"035310","DOI":"10.1103\/PhysRevE.104.035310","article-title":"Variational integrator graph networks for learning energy-conserving dynamical systems","volume":"104","author":"Desai","year":"2021","journal-title":"Phys. Rev. E"},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"147","DOI":"10.1007\/s002200050642","article-title":"Mathematical Physics Discrete Time Lagrangian Mechanics on Lie Groups, with an Application to the Lagrange Top","volume":"204","author":"Bobenko","year":"1999","journal-title":"Commun. Math. Phys."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"253","DOI":"10.1016\/S0393-0440(00)00066-8","article-title":"Variational Methods, Multisymplectic Geometry and Continuum Mechanics","volume":"38","author":"Marsden","year":"2001","journal-title":"J. Geom. Phys."},{"key":"ref_48","unstructured":"Duruisseaux, V., Duong, T., Leok, M., and Atanasov, N. (2023, January 15\u201316). Lie Group Forced Variational Integrator Networks for Learning and Control of Robot Systems. Proceedings of the 5th Annual Conference on Learning for Dynamics and Control, Philadelphia, PA, USA. Available online: http:\/\/arxiv.org\/abs\/2211.16006."},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Lee, J.M. (2012). Introduction to Smooth Manifolds, Springer. [2nd ed.].","DOI":"10.1007\/978-1-4419-9982-5"},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Hall, B.C. (2015). Lie Groups, Lie Algebras, and Representations: An Elementary Introduction, Springer. Graduate Texts in Mathematics (GTM).","DOI":"10.1007\/978-3-319-13467-3"},{"key":"ref_51","unstructured":"Sol\u00e0, J., Deray, J., and Atchuthan, D. (2021). A micro Lie theory for state estimation in robotics. arXiv, Available online: http:\/\/arxiv.org\/abs\/1812.01537."},{"key":"ref_52","first-page":"4187","article-title":"Cayley-Hamilton for roboticists","volume":"1","author":"Visser","year":"2006","journal-title":"IEEE Int. Conf. Intell. Robot. Syst."},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"400","DOI":"10.1214\/aoms\/1177729586","article-title":"A Stochastic Approximation Method","volume":"22","author":"Robbins","year":"1951","journal-title":"Ann. Math. Stat."},{"key":"ref_54","unstructured":"Falorsi, L., de Haan, P., Davidson, T.R., and Forr\u00e9, P. (2019, January 16\u201318). Reparameterizing Distributions on Lie Groups. Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics (AISTATS 2019), Naha, Okinawa, Japan. Available online: http:\/\/arxiv.org\/abs\/1903.02958."},{"key":"ref_55","unstructured":"White, A., Kilbertus, N., Gelbrecht, M., and Boers, N. (2023, January 10\u201316). Stabilized Neural Differential Equations for Learning Dynamics with Explicit Constraints. Proceedings of the 37th Conference on Neural Information Processing Systems (NeurIPS 2023), New Orleans, LA, USA. Available online: http:\/\/arxiv.org\/abs\/2306.09739."},{"key":"ref_56","unstructured":"Poli, M., Massaroli, S., Yamashita, A., Asama, H., and Park, J. (2020). TorchDyn: A Neural Differential Equations Library. arXiv, Available online: http:\/\/arxiv.org\/abs\/2009.09346."},{"key":"ref_57","unstructured":"Schaft, A.V.D., and Jeltsema, D. (2014). Port-Hamiltonian Systems Theory: An Introductory Overview, Now Publishers Inc."},{"key":"ref_58","doi-asserted-by":"crossref","first-page":"1400","DOI":"10.1093\/imamci\/dnaa018","article-title":"Twenty years of distributed port-Hamiltonian systems: A literature review","volume":"37","author":"Rashad","year":"2020","journal-title":"IMA J. Math. Control Inf."},{"key":"ref_59","doi-asserted-by":"crossref","first-page":"3052","DOI":"10.1002\/oca.3025","article-title":"Discovering efficient periodic behaviors in mechanical systems via neural approximators","volume":"44","author":"Wotte","year":"2023","journal-title":"Optim. Control Appl. Methods"},{"key":"ref_60","doi-asserted-by":"crossref","unstructured":"Yao, W. (2023). A Singularity-Free Guiding Vector Field for Robot Navigation, Springer.","DOI":"10.1007\/978-3-031-29152-4"}],"container-title":["Entropy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1099-4300\/27\/8\/878\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:31:18Z","timestamp":1760034678000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1099-4300\/27\/8\/878"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,19]]},"references-count":60,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2025,8]]}},"alternative-id":["e27080878"],"URL":"https:\/\/doi.org\/10.3390\/e27080878","relation":{},"ISSN":["1099-4300"],"issn-type":[{"type":"electronic","value":"1099-4300"}],"subject":[],"published":{"date-parts":[[2025,8,19]]}}}