2000 character limit reached
Learning of Hamiltonian Dynamics with Reproducing Kernel Hilbert Spaces (2312.09734v2)
Published 15 Dec 2023 in cs.RO, cs.LG, cs.SY, and eess.SY
Abstract: This paper presents a method for learning Hamiltonian dynamics from a limited set of data points. The Hamiltonian vector field is found by regularized optimization over a reproducing kernel Hilbert space of vector fields that are inherently Hamiltonian, and where the vector field is required to be odd or even. This is done with a symplectic kernel, and it is shown how this symplectic kernel can be modified to be odd or even. The performance of the method is validated in simulations for two Hamiltonian systems. The simulations show that the learned dynamics reflect the energy-preservation of the Hamiltonian dynamics, and that the restriction to symplectic and odd dynamics gives improved accuracy over a large domain of the phase space.
- V. Sindhwani, S. Tu, and M. Khansari, “Learning Contracting Vector Fields For Stable Imitation Learning,” 2018, arXiv preprint arXiv:1804.04878 [cs.RO].
- A. A. Ahmadi and B. E. Khadir, “Learning Dynamical Systems with Side Information,” in Proceedings of the 2nd Conference on Learning for Dynamics and Control, ser. Proceedings of Machine Learning Research, vol. 120. PMLR, 2020, pp. 718–727.
- S. Singh, S. M. Richards, V. Sindhwani, J.-J. E. Slotine, and M. Pavone, “Learning stabilizable nonlinear dynamics with contraction-based regularization,” The International Journal of Robotics Research, vol. 40, no. 10-11, pp. 1123–1150, 2021.
- M. Revay and I. Manchester, “Contracting Implicit Recurrent Neural Networks: Stable Models with Improved Trainability,” in Proceedings of the 2nd Conference on Learning for Dynamics and Control, ser. Proceedings of Machine Learning Research, vol. 120. PMLR, 2020, pp. 393–403.
- M. Krejnik and A. Tyutin, “Reproducing Kernel Hilbert Spaces With Odd Kernels in Price Prediction,” IEEE Transactions on Neural Networks and Learning Systems, vol. 23, no. 10, pp. 1564–1573, 2012.
- C.-A. Cheng and H.-P. Huang, “Learn the Lagrangian: A Vector-Valued RKHS Approach to Identifying Lagrangian Systems,” IEEE Transactions on Cybernetics, vol. 46, no. 12, pp. 3247–3258, 2016.
- M. Ahmadi, U. Topcu, and C. Rowley, “Control-Oriented Learning of Lagrangian and Hamiltonian Systems,” in American Control Conference (ACC), 2018, pp. 520–525.
- S. Greydanus, M. Dzamba, and J. Yosinski, “Hamiltonian Neural Networks,” in Proceedings of the Conference on Neural Information Processing Systems (NeurIPS), 2019.
- Y. D. Zhong, B. Dey, and A. Chakraborty, “Symplectic ODE-Net: Learning Hamiltonian Dynamics with Control,” in Proceedings of the International Conference on Learning Representations (ICLR), 2020.
- Z. Chen, J. Zhang, M. Arjovsky, and L. Bottou, “Symplectic Recurrent Neural Networks,” in International Conference on Learning Representations, 2020.
- M. Khosravi and R. S. Smith, “Nonlinear System Identification With Prior Knowledge on the Region of Attraction,” IEEE Control Systems Letters, vol. 5, no. 3, pp. 1091–1096, 2021.
- A. J. Thorpe, C. Neary, F. Djeumou, M. M. K. Oishi, and U. Topcu, “Physics-Informed Kernel Embeddings: Integrating Prior System Knowledge with Data-Driven Control,” 2023, arXiv preprint arXiv:2301.03565 [eess.SY].
- N. Aronszajn, “Theory of Reproducing Kernels,” Transactions of the American Mathematical Society, vol. 68, no. 3, pp. 337–404, 1950.
- C. A. Micchelli and M. Pontil, “On Learning Vector-Valued Functions,” Neural Computation, vol. 17, no. 1, pp. 177–204, 2005.
- H. Q. Minh and V. Sindhwani, “Vector-valued manifold regularization,” in Proceedings of the 28’th International Conference on Machine Learning, 2011.
- E. J. Fuselier, “Refined Error Estimates for Matrix-Valued Radial Basis Functions,” 2006, PhD Thesis, Texas A&M University.
- N. M. Boffi, S. Tu, and J.-J. E. Slotine, “Nonparametric adaptive control and prediction: theory and randomized algorithms,” Journal of Machine Learning Research, vol. 23, no. 281, pp. 1–46, 2022.
- R. Kohavi, “A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection,” in Proceedings of the 14th International Joint Conference on Artificial Intelligence, IJCAI-95, 1995, p. 1137–1143.
- A. Rahimi and B. Recht, “Random Features for Large-Scale Kernel Machines,” in Advances in Neural Information Processing Systems, vol. 20, 2007.