Finite sample analysis of system poles for Ho-Kalman algorithm

DOI10.1016/J.JFRANKLIN.2026.108598MaRDI QIDQ7297452zbMATH OpenFDO

Authors Shuai Sun, Xu Wang

Publication date 15 July 2026

Published in Journal of the Franklin Institute (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/J.JFRANKLIN.2026.108598

Mathematics Subject Classification ID

System identification (93B30) Linear systems in control theory (93C05) Sampled-data control/observation systems (93C57)

Cites work

• An optimal bound for the spectral variation of two matrices
• Analysis of state space system identification methods based on instrumental variables and subspace fitting
• Asymptotic least-squares estimation efficiency considerations and applications
• Asymptotic Normality, When Regressors Have a Unit Root
• Consistency and relative efficiency of subspace methods
• Dynamic system identification. Experiment design and data analysis
• Finite sample analysis of MIMO systems identification
• Finite time identification in unstable linear systems
• Finite-Time Identification of Linear Systems: Fundamental Limits and Optimal Algorithms
• Gradient descent learns linear dynamical systems
• Grundzüge der Mengenlehre.
• Handbook of algebra. Volume 4
• High-dimensional probability. An introduction with applications in data science
• High-dimensional statistics. A non-asymptotic viewpoint
• scientific article; zbMATH DE number 3233996 (Why is no real title available?)
• Least-squares estimation of input/output models for distributed linear systems in the presence of noise
• On consistency of subspace methods for system identification
• On the sample complexity of the linear quadratic regulator
• On the singular values of matrices with displacement structure
• Online Learning of the Kalman Filter With Logarithmic Regret
• Probably approximately correct. Nature's algorithms for learning and prospering in a complex world
• Revisiting Ho–Kalman-Based System Identification: Robustness and Finite-Sample Analysis
• Statistical learning theory for control: a finite-sample perspective
• Subspace model identification Part 1. The output-error state-space model identification class of algorithms
• The numerical range is a \((1+\sqrt{2})\)-spectral set

This page was built for publication: Finite sample analysis of system poles for Ho-Kalman algorithm

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7297452)