2000 character limit reached
Error bounds of constant gain least-mean-squares algorithms
Published 20 Jan 2024 in eess.SP, cs.SY, and eess.SY | (2401.11333v1)
Abstract: Constant gain least-mean-squares (LMS) algorithms have a wide range of applications in trajectory tracking problems, but the formal convergence of LMS in mean square is not yet fully established. This work provides an upper bound on the constant gain that guarantees a bounded mean-squared error of LMS for a general design vector. These results highlight the role of the fourth-order moment of the design vector. Numerical examples demonstrate the applicability of this upper bound in setting a constant gain in LMS, while existing criteria may fail. We also provide the associated error bound, which can be applied to design vectors with linearly dependent elements.
- D. Sun, C. Wang, W. Shang, and G. Feng, “A synchronization approach to trajectory tracking of multiple mobile robots while maintaining time-varying formations,” IEEE Transactions on Robotics, vol. 25, pp. 1074–1086, 2009.
- C. Liu, S. Fu, M. Zhang, and H. Ren, “Time-varying hydrodynamics of a flexible riser under multi-frequency vortex-induced vibrations,” Journal of Fluids and Structures, vol. 80, pp. 217–244, 2018.
- C. Liu, S. Fu, M. Zhang, H. Ren, and Y. Xu, “Hydrodynamics of a flexible cylinder under modulated vortex-induced vibrations,” Journal of Fluids and Structures, vol. 94, p. 102913, 2020.
- H. Zhang, C. W. Rowley, E. A. Deem, and L. N. Cattafesta, “Online dynamic mode decomposition for time-varying systems,” SIAM Journal on Applied Dynamical Systems, vol. 18, pp. 1586–1609, 2019.
- T. Tsubota, C. Liu, B. Foster, and E. Knobloch, “Bifurcation delay and front propagation in the real Ginzburg-Landau equation on a time-dependent domain,” arXiv preprint arXiv:2311.16363, 2023.
- L. Guo and L. Ljung, “Exponential stability of general tracking algorithms,” IEEE Transactions on Automatic Control, vol. 40, pp. 1376–1387, 1995.
- ——, “Performance analysis of general tracking algorithms,” IEEE Transactions on Automatic Control, vol. 40, pp. 1388–1402, 1995.
- L. Guo, L. Ljung, and G.-J. Wang, “Necessary and sufficient conditions for stability of LMS,” IEEE Transactions on Automatic Control, vol. 42, pp. 761–770, 1997.
- H. J. Kushner and H. Huang, “Asymptotic properties of stochastic approximations with constant coefficients,” SIAM Journal on Control and Optimization, vol. 19, pp. 87–105, 1981.
- O. Macchi and E. Eweda, “Second-order convergence analysis of stochastic adaptive linear filtering,” IEEE Transactions on Automatic Control, vol. 28, pp. 76–85, 1983.
- L. Gerencsér, “Rate of convergence of the LMS method,” Systems &\&& Control Letters, vol. 24, pp. 385–388, 1995.
- Z.-Q. Wang, M. T. Manry, and J. L. Schiano, “LMS learning algorithms: misconceptions and new results on converence,” IEEE Transactions on Neural Networks, vol. 11, pp. 47–56, 2000.
- B. Widrow and S. D. Stearns, “Adaptive signal processing,” Englewood Cliffs, NJ, 1985.
- J. Zhu and J. C. Spall, “Error bound analysis of the least-mean-squares algorithm in linear models,” in 2015 49th Annual Conference on Information Sciences and Systems (CISS). IEEE, 2015, pp. 1–6.
- ——, “Tracking capability of stochastic gradient algorithm with constant gain,” in 2016 IEEE 55th Conference on Decision and Control (CDC). IEEE, 2016, pp. 4522–4527.
- ——, “Probabilistic bounds in tracking a discrete-time varying process,” in 2018 IEEE Conference on Decision and Control (CDC). IEEE, 2018, pp. 4849–4854.
- ——, “Stochastic approximation with nondecaying gain: Error bound and data-driven gain-tuning,” International Journal of Robust and Nonlinear Control, vol. 30, pp. 5820–5870, 2020.
- J. Zhu, “Error bounds and applications for stochastic approximation with non-decaying gain,” Ph.D. dissertation, Johns Hopkins University, 2020.
- C. Liu and D. F. Gayme, “Input-output inspired method for permissible perturbation amplitude of transitional wall-bounded shear flows,” Physical Review E, vol. 102, p. 063108, 2020.
- J. Löfberg, “YALMIP: A toolbox for modeling and optimization in MATLAB,” in Proceedings of the CACSD Conference, vol. 3. Taipei, Taiwan, 2004.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.