2000 character limit reached
Learning Stable and Passive Neural Differential Equations (2404.12554v2)
Published 19 Apr 2024 in eess.SY, cs.LG, and cs.SY
Abstract: In this paper, we introduce a novel class of neural differential equation, which are intrinsically Lyapunov stable, exponentially stable or passive. We take a recently proposed Polyak Lojasiewicz network (PLNet) as an Lyapunov function and then parameterize the vector field as the descent directions of the Lyapunov function. The resulting models have a same structure as the general Hamiltonian dynamics, where the Hamiltonian is lower- and upper-bounded by quadratic functions. Moreover, it is also positive definite w.r.t. either a known or learnable equilibrium. We illustrate the effectiveness of the proposed model on a damped double pendulum system.
- K. Hornik, M. Stinchcombe, and H. White, “Multilayer feedforward networks are universal approximators,” Neural networks, vol. 2, no. 5, pp. 359–366, 1989.
- R. T. Chen, Y. Rubanova, J. Bettencourt, and D. K. Duvenaud, “Neural ordinary differential equations,” Advances in neural information processing systems, vol. 31, 2018.
- M. M. Tobenkin, I. R. Manchester, J. Wang, A. Megretski, and R. Tedrake, “Convex optimization in identification of stable non-linear state space models,” in 49th IEEE Conference on Decision and Control (CDC), pp. 7232–7237, IEEE, 2010.
- S. M. Khansari-Zadeh and A. Billard, “Learning stable nonlinear dynamical systems with gaussian mixture models,” IEEE Transactions on Robotics, vol. 27, no. 5, pp. 943–957, 2011.
- M. M. Tobenkin, I. R. Manchester, and A. Megretski, “Convex parameterizations and fidelity bounds for nonlinear identification and reduced-order modelling,” IEEE Transactions on Automatic Control, vol. 62, no. 7, pp. 3679–3686, 2017.
- J. Umenberger, J. Wågberg, I. R. Manchester, and T. B. Schön, “Maximum likelihood identification of stable linear dynamical systems,” Automatica, vol. 96, pp. 280–292, 2018.
- W. Lohmiller and J.-J. E. Slotine, “On contraction analysis for non-linear systems,” Automatica, vol. 34, no. 6, pp. 683–696, 1998.
- M. Revay and I. Manchester, “Contracting implicit recurrent neural networks: Stable models with improved trainability,” in Learning for Dynamics and Control, pp. 393–403, PMLR, 2020.
- M. Revay, R. Wang, and I. R. Manchester, “Recurrent equilibrium networks: Flexible dynamic models with guaranteed stability and robustness,” IEEE Transactions on Automatic Control, 2023.
- F. Fan, B. Yi, D. Rye, G. Shi, and I. R. Manchester, “Learning stable koopman embeddings for identification and control,” arXiv preprint arXiv:2401.08153, 2024.
- D. Martinelli, C. L. Galimberti, I. R. Manchester, L. Furieri, and G. Ferrari-Trecate, “Unconstrained parametrization of dissipative and contracting neural ordinary differential equations,” in 2023 62nd IEEE Conference on Decision and Control (CDC), pp. 3043–3048, IEEE, 2023.
- F. Wilson Jr, “The structure of the level surfaces of a lyapunov function,” 1967.
- M. T. Anderson, “Geometrization of 3-manifolds via the ricci flow,” Notices AMS, vol. 51, pp. 184–193, 2004.
- S. M. Richards, F. Berkenkamp, and A. Krause, “The lyapunov neural network: Adaptive stability certification for safe learning of dynamical systems,” in Conference on Robot Learning, pp. 466–476, PMLR, 2018.
- J. Z. Kolter and G. Manek, “Learning stable deep dynamics models,” Advances in neural information processing systems, vol. 32, 2019.
- B. Amos, L. Xu, and J. Z. Kolter, “Input convex neural networks,” in International Conference on Machine Learning (ICML), pp. 146–155, PMLR, 2017.
- C. Dawson, S. Gao, and C. Fan, “Safe control with learned certificates: A survey of neural lyapunov, barrier, and contraction methods for robotics and control,” IEEE Transactions on Robotics, 2023.
- R. Wang, K. Dvijotham, and I. R. Manchester, “Monotone, bi-Lipschitz, and Polyak-Lojasiewicz networks,” arXiv preprint arXiv:2402.01344, 2024.
- A. Van Der Schaft, D. Jeltsema, et al., “Port-hamiltonian systems theory: An introductory overview,” Foundations and Trends® in Systems and Control, vol. 1, no. 2-3, pp. 173–378, 2014.
- Springer Science & Business Media, 2009.
- H. K. Khalil, Nonlinear systems. Prentice Hall, New York, NY, 2002.
- R. T. Chen, J. Behrmann, D. K. Duvenaud, and J.-H. Jacobsen, “Residual flows for invertible generative modeling,” Advances in Neural Information Processing Systems, vol. 32, 2019.
- J. Behrmann, W. Grathwohl, R. T. Chen, D. Duvenaud, and J.-H. Jacobsen, “Invertible residual networks,” in International conference on machine learning (ICML), pp. 573–582, PMLR, 2019.
- C. Lu, J. Chen, C. Li, Q. Wang, and J. Zhu, “Implicit normalizing flows,” in International Conference on Learning Representations (ICLR), 2021.
- B. Ahn, C. Kim, Y. Hong, and H. J. Kim, “Invertible monotone operators for normalizing flows,” Advances in Neural Information Processing Systems, vol. 35, pp. 16836–16848, 2022.
- B. Polyak, “Gradient methods for minimizing functionals (in russian),” USSR Computational Mathematics and Mathematical Physics, vol. 3, no. 4, pp. 643–653, 1963.
- S. Lojasiewicz, “A topological property of real analytic subsets,” Coll. du CNRS, Les équations aux dérivées partielles, vol. 117, no. 87-89, p. 2, 1963.
- Springer Science & Business Media, 2007.
- D. P. Kingma and J. Ba, “Adam: A method for stochastic optimization,” in International Conference on Learning Representations (ICLR), 2015.