Kernels for linear time invariant system identification

DOI10.1137/130920319MaRDI QIDQ3451766zbMATH OpenOpenAlexFDO

Authors Francesco Dinuzzo

Publication date 18 November 2015

Published in SIAM Journal on Control and Optimization (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1203.4930

zbMATH Keywords

regularizationreproducing kernel Hilbert spacessystem identification

Mathematics Subject Classification ID

Hilbert spaces with reproducing kernels (= (proper) functional Hilbert spaces, including de Branges-Rovnyak and other structured spaces) (46E22) System identification (93B30) Linear operators and ill-posed problems, regularization (47A52)

Abstract: In this paper, we study the problem of identifying the impulse response of a linear time invariant (LTI) dynamical system from the knowledge of the input signal and a finite set of noisy output observations. We adopt an approach based on regularization in a Reproducing Kernel Hilbert Space (RKHS) that takes into account both continuous and discrete time systems. The focus of the paper is on designing spaces that are well suited for temporal impulse response modeling. To this end, we construct and characterize general families of kernels that incorporate system properties such as stability, relative degree, absence of oscillatory behavior, smoothness, or delay. In addition, we discuss the possibility of automatically searching over these classes by means of kernel learning techniques, so as to capture different modes of the system to be identified.

Recommendations

• A new kernel-based approach for linear system identification
• The quest for the right kernel in Bayesian impulse response identification: the use of OBFs
• Kernel methods in system identification, machine learning and function estimation: a survey
• On kernel design for regularized LTI system identification
• System identification using kernel-based regularization: new insights on stability and consistency issues

Cites work

• scientific article; zbMATH DE number 45848 (Why is no real title available?)
• scientific article; zbMATH DE number 3551792 (Why is no real title available?)
• scientific article; zbMATH DE number 3997615 (Why is no real title available?)
• 10.1162/15324430152748236
• A new kernel-based approach for linear system identification
• Dissipative dynamical systems. II: Linear systems with quadratic supply rates
• Gaussian processes for machine learning.
• Identification of stable models in subspace identification by using regularization
• Interior-point method for nuclear norm approximation with application to system identification
• Kernel methods in system identification, machine learning and function estimation: a survey
• Learning Theory
• Learning the kernel function via regularization
• On the estimation of transfer functions, regularizations and Gaussian processes-revisited
• Smoothing noisy data with spline functions: Estimating the correct degree of smoothing by the method of generalized cross-validation
• Some results on Tchebycheffian spline functions and stochastic processes
• Support Vector Machines
• System Identification Via Sparse Multiple Kernel-Based Regularization Using Sequential Convex Optimization Techniques
• Theory of Reproducing Kernels
• VECTOR VALUED REPRODUCING KERNEL HILBERT SPACES OF INTEGRABLE FUNCTIONS AND MERCER THEOREM

Cited in

(47)

• Kernel absolute summability is sufficient but not necessary for RKHS stability
• The harmonic analysis of kernel functions
• Robust EM kernel-based methods for linear system identification
• High precision variational Bayesian inference of sparse linear networks
• On the mathematical foundations of stable RKHSs
• Maximum Entropy Kernels for System Identification
• Kernel methods in system identification, machine learning and function estimation: a survey
• Kernel-Based Models for System Analysis
• A scaled gradient projection method for Bayesian learning in dynamical systems
• Identification of non-linear time series via kernels
• Identification of Time-Varying Systems in Reproducing Kernel Hilbert Spaces
• A new kernel-based approach for linear system identification
• FRF estimation using multiple kernel-based regularisation
• When cannot regularization improve the least squares estimate in the kernel-based regularized system identification
• Kernel-based identification of asymptotically stable continuous-time linear dynamical systems
• scientific article; zbMATH DE number 7652341 (Why is no real title available?)
• On semiseparable kernels and efficient implementation for regularized system identification and function estimation
• Regularized nonparametric Volterra kernel estimation
• On the stability of reproducing kernel Hilbert spaces of discrete-time impulse responses
• Mercer kernel absolute integrability is only sufficient for RKHS stability
• Stable spline identification of linear systems under missing data
• On kernel design for regularized LTI system identification
• A shift in paradigm for system identification
• Informative input design for kernel-based system identification
• System identification using kernel-based regularization: new insights on stability and consistency issues
• On asymptotic properties of hyperparameter estimators for kernel-based regularization methods
• Control-oriented regularization for linear system identification
• Kernel-based system identification with manifold regularization: a Bayesian perspective
• Joint input-output identification of unstable systems with kernel regularization
• Bayesian nonparametric identification of Wiener systems
• Kernel-based identification of non-causal systems with application to inverse model control
• A nonparametric kernel-based approach to Hammerstein system identification
• Analysis of Variance of Tensor Product Reproducing Kernel Hilbert Spaces on Metric Spaces
• Real-time identification of time-varying systems by non-parametric algorithms based on Parzen kernels
• The existence and uniqueness of solutions for kernel-based system identification
• Leading impulse response identification via the elastic net criterion
• State-space LPV model identification using kernelized machine learning
• Reconstruction of linear and non-linear continuous-time system models from input/output data using the kernel invariance algorithm
• Regularized identification with internal positivity side-information
• On convexification of system identification criteria
• Beurling-type density criteria for system identification
• Kernel-based linear system identification: when does the representer theorem hold?
• On kernel design for regularized non-causal system identification
• A graph learning approach for kernel-based system identification with manifold regularization
• A refinement of the stability test for reproducing kernel Hilbert spaces
• Kernel-based identification using Lebesgue-sampled data
• The quest for the right kernel in Bayesian impulse response identification: the use of OBFs

This page was built for publication: Kernels for linear time invariant system identification

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3451766)