Guardado en:
Detalles Bibliográficos
Autores principales: Li, Jiayun, Lu, Yiwen, Mo, Yilin
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2409.05390
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866929492193181696
author Li, Jiayun
Lu, Yiwen
Mo, Yilin
author_facet Li, Jiayun
Lu, Yiwen
Mo, Yilin
contents This paper considers the output prediction problem for an unknown Linear Time-Invariant (LTI) system. In particular, we focus our attention on the OBF-ARX filter, whose transfer function is a linear combination of Orthogonal Basis Functions (OBFs), with the coefficients determined by solving a least-squares regression. We prove that the OBF-ARX filter is an accurate approximation of the Kalman Filter (KF) by quantifying its online performance. Specifically, we analyze the average regret between the OBF-ARX filter and the KF, proving that the average regret over $N$ time steps converges to the asymptotic bias at the speed of $O(N^{-0.5+ε})$ almost surely for all $ε>0$. Then, we establish an upper bound on the asymptotic bias, demonstrating that it decreases exponentially with the number of OBF bases, and the decreasing rate $τ(\boldsymbolλ, \boldsymbolμ)$ explicitly depends on the poles of both the KF and the OBF. Numerical results on diffusion processes validate the derived bounds.
format Preprint
id arxiv_https___arxiv_org_abs_2409_05390
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Regret Analysis with Almost Sure Convergence for OBF-ARX Filter
Li, Jiayun
Lu, Yiwen
Mo, Yilin
Optimization and Control
This paper considers the output prediction problem for an unknown Linear Time-Invariant (LTI) system. In particular, we focus our attention on the OBF-ARX filter, whose transfer function is a linear combination of Orthogonal Basis Functions (OBFs), with the coefficients determined by solving a least-squares regression. We prove that the OBF-ARX filter is an accurate approximation of the Kalman Filter (KF) by quantifying its online performance. Specifically, we analyze the average regret between the OBF-ARX filter and the KF, proving that the average regret over $N$ time steps converges to the asymptotic bias at the speed of $O(N^{-0.5+ε})$ almost surely for all $ε>0$. Then, we establish an upper bound on the asymptotic bias, demonstrating that it decreases exponentially with the number of OBF bases, and the decreasing rate $τ(\boldsymbolλ, \boldsymbolμ)$ explicitly depends on the poles of both the KF and the OBF. Numerical results on diffusion processes validate the derived bounds.
title Regret Analysis with Almost Sure Convergence for OBF-ARX Filter
topic Optimization and Control
url https://arxiv.org/abs/2409.05390