Kernel Absolute Summability Is Sufficient but Not Necessary for RKHS Stability

DOI10.1137/19M1278442zbMath1445.47056arXiv1909.02341OpenAlexW3045302579MaRDI QIDQ3300839

Mauro Bisiacco, Gianluigi Pillonetto

Publication date: 30 July 2020

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

Full work available at URL: https://arxiv.org/abs/1909.02341

zbMATH Keywords

BIBO stabilityreproducing kernel Hilbert spacesabsolute summabilitydiscrete-time impulse responseslinear and bounded operators

Mathematics Subject Classification ID

Ill-posedness and regularization problems in numerical linear algebra (65F22) System identification (93B30) Identification in stochastic control theory (93E12) Hilbert spaces with reproducing kernels (= (proper) functional Hilbert spaces, including de Branges-Rovnyak and other structured spaces) (46E22) Applications of operator theory in systems, signals, circuits, and control theory (47N70) Linear operators and ill-posed problems, regularization (47A52)

Related Items (2)

The existence and uniqueness of solutions for kernel-based system identification ⋮ Sparse estimation in linear dynamic networks using the stable spline horseshoe prior

Uses Software

• ElemStatLearn
• IPsolve

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Maximum entropy properties of discrete-time first-order stable spline kernel
• Robust EM kernel-based methods for linear system identification
• 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
• A new kernel-based approach for linear system identification
• Estimating the dimension of a model
• Bauer's maximum principle and hulls of sets
• On the stability of reproducing kernel Hilbert spaces of discrete-time impulse responses
• On kernel design for regularized LTI system identification
• Regularization networks and support vector machines
• Stochastic processes with sample paths in reproducing kernel Hilbert spaces
• Regularization Algorithms for Learning That Are Equivalent to Multilayer Networks
• Estimating parameters and stochastic functions of one variable using nonlinear measurement models
• VECTOR VALUED REPRODUCING KERNEL HILBERT SPACES OF INTEGRABLE FUNCTIONS AND MERCER THEOREM
• Kernels for Linear Time Invariant System Identification
• Generalized System Identification with Stable Spline Kernels
• Convex Analysis
• A Correspondence Between Bayesian Estimation on Stochastic Processes and Smoothing by Splines
• The elements of statistical learning. Data mining, inference, and prediction
• A new look at the statistical model identification

This page was built for publication: Kernel Absolute Summability Is Sufficient but Not Necessary for RKHS Stability