A least-square method for non-asymptotic identification in linear switching control (2404.08120v1)
Abstract: The focus of this paper is on linear system identification in the setting where it is known that the underlying partially-observed linear dynamical system lies within a finite collection of known candidate models. We first consider the problem of identification from a given trajectory, which in this setting reduces to identifying the index of the true model with high probability. We characterize the finite-time sample complexity of this problem by leveraging recent advances in the non-asymptotic analysis of linear least-square methods in the literature. In comparison to the earlier results that assume no prior knowledge of the system, our approach takes advantage of the smaller hypothesis class and leads to the design of a learner with a dimension-free sample complexity bound. Next, we consider the switching control of linear systems, where there is a candidate controller for each of the candidate models and data is collected through interaction of the system with a collection of potentially destabilizing controllers. We develop a dimension-dependent criterion that can detect those destabilizing controllers in finite time. By leveraging these results, we propose a data-driven switching strategy that identifies the unknown parameters of the underlying system. We then provide a non-asymptotic analysis of its performance and discuss its implications on the classical method of estimator-based supervisory control.
- Improved algorithms for linear stochastic bandits. Advances in neural information processing systems, 24, 2011.
- Trajectory-tracking and path-following of underactuated autonomous vehicles with parametric modeling uncertainty. IEEE transactions on automatic control, 52(8):1362–1379, 2007.
- Lyapunov-based switching supervisory control of nonlinear uncertain systems. IEEE Transactions on Automatic Control, 47(3):500–505, 2002.
- A new approach to learning linear dynamical systems. In Proceedings of the 55th Annual ACM Symposium on Theory of Computing, pages 335–348, 2023.
- Hysteresis-based supervisory control with application to non-pharmaceutical containment of covid-19. Annual reviews in control, 52:508–522, 2021.
- Discrete-time supervisory control of families of two-degrees-of-freedom linear set-point controllers. IEEE Transactions on Automatic Control, 44(1):178–181, 1999.
- Finite time identification in unstable linear systems. Automatica, 96, 2018.
- Joao P Hespanha. Tutorial on supervisory control. In Lecture Notes for the workshop Control using Logic and Switching for the 40th Conf. on Decision and Contr., Orlando, Florida, 2001.
- Certainty equivalence implies detectability. Systems & Control Letters, 36(1), 1999.
- Adaptive estimation of a quadratic functional by model selection. Annals of statistics, pages 1302–1338, 2000.
- Online switching control with stability and regret guarantees. In Learning for Dynamics and Control Conference, 2023.
- Daniel Liberzon. Switching in systems and control, volume 190. Springer.
- Lennart Ljung. System identification. In Signal analysis and prediction, pages 163–173. Springer, 1998.
- Microgrid supervisory controllers and energy management systems: A literature review. Renewable and Sustainable Energy Reviews, 60:1263–1273, 2016.
- A Stephen Morse. Supervisory control of families of linear set-point controllers-part i. exact matching. IEEE transactions on Automatic Control, 41(10):1413–1431, 1996.
- A. Stephen Morse. Supervisory control of families of linear set-point controllers. 2. robustness. IEEE Transactions on Automatic Control, 42(11):1500–1515, 1997.
- Non-asymptotic identification of lti systems from a single trajectory. In 2019 American control conference (ACC), pages 5655–5661. IEEE, 2019.
- Stability overlay for adaptive control laws. Automatica, 47(5):1007–1014, 2011.
- Hanson-wright inequality and sub-gaussian concentration. 2013.
- The unfalsified control concept and learning. In Proceedings of 1994 33rd IEEE conference on decision and control, volume 3, pages 2819–2824. IEEE, 1994.
- Near optimal finite time identification of arbitrary linear dynamical systems. In International Conference on Machine Learning, pages 5610–5618. PMLR, 2019.
- Finite time lti system identification. Journal of Machine Learning Research, 22(26):1–61, 2021.
- Naive exploration is optimal for online lqr. In International Conference on Machine Learning, 2020.
- Learning without mixing: Towards a sharp analysis of linear system identification. In Conference On Learning Theory, pages 439–473, 2018.
- Learning linear dynamical systems with semi-parametric least squares. In Conference on Learning Theory, pages 2714–2802. PMLR, 2019.
- Safe adaptive switching control: Stability and convergence. IEEE Transactions on Automatic Control, 53(9):2012–2021, 2008.
- Can direct latent model learning solve linear quadratic gaussian control? In Learning for Dynamics and Control Conference, pages 51–63. PMLR, 2023.
- Paolo Tilli. Singular values and eigenvalues of non-hermitian block toeplitz matrices. Linear algebra and its applications, 272(1-3):59–89, 1998.
- Learning with little mixing. Advances in Neural Information Processing Systems, 35:4626–4637, 2022.
- A tutorial on the non-asymptotic theory of system identification. In Conference on Decision and Control (CDC). IEEE, 2023.