Second-order optimization methods for time-delay Autoregressive eXogenous models: Nature gradient descent method and its two modified methods

Chen, Jing; Pu, Yan; Guo, Liuxiao; Cao, Junfeng; Zhu, Quanmin

Abstract

This article proposes several second-order optimization methods for time-delay ARX model. Since the time-delay in the information vector makes the traditional identification algorithms be inefficient, a redundant rule based method is utilized to transformed the model into a redundant model. Then, the nature gradient descent (NGD) algorithm is developed for such a model. To reduce the computational efforts of the NGD algorithm and to adaptively update each element in the parameter vector, two modified NGD algorithms are also presented. The simulation examples verify the effectiveness of the proposed algorithms.

Citation

Chen, J., Pu, Y., Guo, L., Cao, J., & Zhu, Q. (2023). Second-order optimization methods for time-delay Autoregressive eXogenous models: Nature gradient descent method and its two modified methods. International Journal of Adaptive Control and Signal Processing, 37(1), 211-223. https://doi.org/10.1002/acs.3519

• Journal Article Type: Article
• Acceptance Date: Oct 8, 2022
• Online Publication Date: Oct 25, 2022
• Publication Date: Jan 1, 2023
• Deposit Date: Nov 8, 2022
• Publicly Available Date: Oct 26, 2023
• Journal: International Journal of Adaptive Control and Signal Processing
• Print ISSN: 0890-6327
• Electronic ISSN: 1099-1115
• Publisher: Wiley
• Peer Reviewed: Peer Reviewed
• Volume: 37
• Issue: 1
• Pages: 211-223
• DOI: https://doi.org/10.1002/acs.3519
• Keywords: Electrical and Electronic Engineering, Signal Processing, Control and Systems Engineering, ARX model, Time-delay, Nature gradient descent, Adaptive gradient descent, Momentum based method, Convergence rate
• Public URL: https://uwe-repository.worktribe.com/output/10121748
• Publisher URL: https://onlinelibrary.wiley.com/doi/10.1002/acs.3519