Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
143 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
46 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Unconstrained learning of networked nonlinear systems via free parametrization of stable interconnected operators (2311.13967v3)

Published 23 Nov 2023 in eess.SY and cs.SY

Abstract: This paper characterizes a new parametrization of nonlinear networked incrementally $L_2$-bounded operators in discrete time. The distinctive novelty is that our parametrization is \emph{free} -- that is, a sparse large-scale operator with bounded incremental $L_2$ gain is obtained for any choice of the real values of our parameters. This property allows one to freely search over optimal parameters via unconstrained gradient descent, enabling direct applications in large-scale optimal control and system identification. Further, we can embed prior knowledge about the interconnection topology and stability properties of the system directly into the large-scale distributed operator we design. Our approach is extremely general in that it can seamlessly encapsulate and interconnect state-of-the-art Neural Network (NN) parametrizations of stable dynamical systems. To demonstrate the effectiveness of this approach, we provide a simulation example showcasing the identification of a networked nonlinear system. The results underscore the superiority of our free parametrizations over standard NN-based identification methods where a prior over the system topology and local stability properties are not enforced.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (23)
  1. L. Ljung, “System identification,” in Signal analysis and prediction.   Springer, 1998, pp. 163–173.
  2. P. J. Koelewijn and R. Tóth, “Incremental stability and performance analysis of discrete-time nonlinear systems using the lpv framework,” IFAC-PapersOnLine, vol. 54, no. 8, pp. 75–82, 2021.
  3. J. C. Willems, “Dissipative dynamical systems part i: General theory,” Archive for rational mechanics and analysis, vol. 45, no. 5, pp. 321–351, 1972.
  4. C. I. Byrnes and W. Lin, “Losslessness, feedback equivalence, and the global stabilization of discrete-time nonlinear systems,” IEEE Transactions on automatic control, vol. 39, no. 1, pp. 83–98, 1994.
  5. T. Rajpurohit and W. M. Haddad, “Dissipativity theory for nonlinear stochastic dynamical systems,” IEEE Transactions on Automatic Control, vol. 62, no. 4, pp. 1684–1699, 2016.
  6. C. Verhoek, P. J. Koelewijn, S. Haesaert, and R. Tóth, “Convex incremental dissipativity analysis of nonlinear systems,” Automatica, vol. 150, p. 110859, 2023.
  7. D. Hill and P. Moylan, “The stability of nonlinear dissipative systems,” IEEE transactions on automatic control, vol. 21, no. 5, pp. 708–711, 1976.
  8. D. Angeli, “A lyapunov approach to incremental stability properties,” IEEE Transactions on Automatic Control, vol. 47, no. 3, pp. 410–421, 2002.
  9. A. Pavlov and L. Marconi, “Incremental passivity and output regulation,” Systems & Control Letters, vol. 57, no. 5, pp. 400–409, 2008.
  10. P. Moylan and D. Hill, “Stability criteria for large-scale systems,” IEEE Transactions on Automatic Control, vol. 23, no. 2, pp. 143–149, 1978.
  11. M. Inoue and K. Urata, “Dissipativity reinforcement in interconnected systems,” Automatica, vol. 95, pp. 73–85, 2018.
  12. 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.
  13. ——, “Recurrent equilibrium networks: Flexible dynamic models with guaranteed stability and robustness,” arXiv preprint arXiv:2104.05942, 2021.
  14. D. Martinelli, C. L. Galimberti, I. R. Manchester, L. Furieri, and G. Ferrari-Trecate, “Unconstrained parametrization of dissipative and contracting neural ordinary differential equations,” arXiv preprint arXiv:2304.02976, 2023.
  15. E. Terzi, T. Bonetti, D. Saccani, M. Farina, L. Fagiano, and R. Scattolini, “Learning-based predictive control of the cooling system of a large business centre,” Control Engineering Practice, vol. 97, p. 104348, 2020.
  16. S. Chen, S. A. Billings, and P. Grant, “Non-linear system identification using neural networks,” International journal of control, vol. 51, no. 6, pp. 1191–1214, 1990.
  17. M. Zakwan, L. Di Natale, B. Svetozarevic, P. Heer, C. N. Jones, and G. F. Trecate, “Physically consistent neural odes for learning multi-physics systems,” arXiv preprint arXiv:2211.06130, 2022.
  18. L. Furieri, C. L. Galimberti, and G. Ferrari-Trecate, “Neural system level synthesis: Learning over all stabilizing policies for nonlinear systems,” in 2022 IEEE 61st Conference on Decision and Control (CDC).   IEEE, 2022, pp. 2765–2770.
  19. S. Dashkovskiy, B. S. Rüffer, and F. R. Wirth, “An iss small gain theorem for general networks,” Mathematics of Control, Signals, and Systems, vol. 19, pp. 93–122, 2007.
  20. G. Chesi, “Exact lmi conditions for stability and l2 gain analysis of 2-d mixed continuous–discrete time systems via quadratically frequency-dependent lyapunov functions,” IEEE Transactions on Automatic Control, vol. 67, no. 3, pp. 1147–1162, 2021.
  21. H. N. Salas, “Gershgorin’s theorem for matrices of operators,” Linear algebra and its applications, vol. 291, no. 1-3, pp. 15–36, 1999.
  22. P. J. Werbos, “Backpropagation through time: what it does and how to do it,” Proceedings of the IEEE, vol. 78, no. 10, pp. 1550–1560, 1990.
  23. L. R. Medsker and L. Jain, “Recurrent neural networks,” Design and Applications, vol. 5, no. 64-67, p. 2, 2001.
Citations (3)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now