On the stability of reproducing kernel Hilbert spaces of discrete-time impulse responses

DOI10.1016/j.automatica.2018.05.017zbMath1402.93091OpenAlexW2809340333MaRDI QIDQ1626948

Tianshi Chen, Gianluigi Pillonetto

Publication date: 21 November 2018

Published in: Automatica (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.automatica.2018.05.017

zbMATH Keywords

BIBO stabilityinverse problemsreproducing kernel Hilbert spaceskernel-based regularizationlinear system identification

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) System identification (93B30) Discrete-time control/observation systems (93C55) Lyapunov and other classical stabilities (Lagrange, Poisson, (L^p, l^p), etc.) in control theory (93D05) Linear systems in control theory (93C05) Control/observation systems in abstract spaces (93C25)

Related Items (9)

On the mathematical foundations of stable RKHSs ⋮ The existence and uniqueness of solutions for kernel-based system identification ⋮ When cannot regularization improve the least squares estimate in the kernel-based regularized system identification ⋮ Kernel-based identification with frequency domain side-information ⋮ Kernel Absolute Summability Is Sufficient but Not Necessary for RKHS Stability ⋮ On asymptotic properties of hyperparameter estimators for kernel-based regularization methods ⋮ Separable multi‐innovation stochastic gradient estimation algorithm for the nonlinear dynamic responses of systems ⋮ Maximum likelihood iterative identification approaches for multivariable equation-error moving average systems ⋮ Decomposition strategy-based hierarchical least mean square algorithm for control systems from the impulse responses

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Kernel methods in system identification, machine learning and function estimation: a survey
• Prediction error identification of linear systems: a nonparametric Gaussian regression approach
• On covariance function tests used in system identification
• A new kernel-based approach for linear system identification
• Applied functional analysis. Main principles and their applications
• Regularization networks and support vector machines
• On the estimation of transfer functions, regularizations and Gaussian processes-revisited
• Learning theory estimates via integral operators and their approximations
• Stochastic processes with sample paths in reproducing kernel Hilbert spaces
• On the mathematical foundations of learning
• System Identification Via Sparse Multiple Kernel-Based Regularization Using Sequential Convex Optimization Techniques
• Regularization Algorithms for Learning That Are Equivalent to Multilayer Networks
• VECTOR VALUED REPRODUCING KERNEL HILBERT SPACES OF INTEGRABLE FUNCTIONS AND MERCER THEOREM
• Kernels for Linear Time Invariant System Identification
• An Explicit Description of the Reproducing Kernel Hilbert Spaces of Gaussian RBF Kernels
• An Introduction to Banach Space Theory
• A Correspondence Between Bayesian Estimation on Stochastic Processes and Smoothing by Splines
• Theory of Reproducing Kernels

This page was built for publication: On the stability of reproducing kernel Hilbert spaces of discrete-time impulse responses