When cannot regularization improve the least squares estimate in the kernel-based regularized system identification

DOI10.1016/j.automatica.2023.111442OpenAlexW4389558852MaRDI QIDQ6152563

Bi-Qiang Mu, Tianshi Chen, Lennart Ljung

Publication date: 13 February 2024

Published in: Automatica (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.automatica.2023.111442

zbMATH Keywords

least squaresregularized least squaressquared error criterion

Mathematics Subject Classification ID

Least squares and related methods for stochastic control systems (93E24) Identification in stochastic control theory (93E12) Impulsive control/observation systems (93C27)

Cites Work

• Unnamed Item
• Maximum entropy properties of discrete-time first-order stable spline kernel
• Regularized linear system identification using atomic, nuclear and kernel-based norms: the role of the stability constraint
• Kernel methods in system identification, machine learning and function estimation: a survey
• Prediction error identification of linear systems: a nonparametric Gaussian regression approach
• The quest for the right kernel in Bayesian impulse response identification: the use of OBFs
• Tuning complexity in regularized kernel-based regression and linear system identification: the robustness of the marginal likelihood estimator
• A new kernel-based approach for linear system identification
• Asymptotic optimality of \(C_ L\) and generalized cross-validation in ridge regression with application to spline smoothing
• On the stability of reproducing kernel Hilbert spaces of discrete-time impulse responses
• On kernel design for regularized LTI system identification
• The harmonic analysis of kernel functions
• On asymptotic properties of hyperparameter estimators for kernel-based regularization methods
• Regularized system identification. Learning dynamic models from data
• Adaptive regularised kernel-based identification method for large-scale systems with unknown order
• On the mathematical foundations of stable RKHSs
• On the estimation of transfer functions, regularizations and Gaussian processes-revisited
• The existence and uniqueness of solutions for kernel-based system identification
• System Identification Via Sparse Multiple Kernel-Based Regularization Using Sequential Convex Optimization Techniques
• Kernels for Linear Time Invariant System Identification
• A shift in paradigm for system identification
• Maximum Entropy Kernels for System Identification