Some properties of Gaussian reproducing kernel Hilbert spaces and their implications for function approximation and learning theory

DOI10.1007/S00365-009-9080-0zbMATH Open1204.68157OpenAlexW1993288992MaRDI QIDQ5962345FDOQ5962345

Authors: Hà Quang Minh 

Publication date: 22 September 2010

Published in: Constructive Approximation (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s00365-009-9080-0

Recommendations

• An Explicit Description of the Reproducing Kernel Hilbert Spaces of Gaussian RBF Kernels
• Derivative reproducing properties for kernel methods in learning theory
• Approximating functions in reproducing kernel Hilbert spaces via statistical learning theory
• Frames, reproducing kernels, regularization and learning
• Learning rates of least-square regularized regression

zbMATH Keywords

learning theoryeigenvaluesreproducing kernel Hilbert spacesGaussian kernelregularized least square algorithm

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Coding and information theory (compaction, compression, models of communication, encoding schemes, etc.) (aspects in computer science) (68P30)

Cites Work

• VECTOR VALUED REPRODUCING KERNEL HILBERT SPACES OF INTEGRABLE FUNCTIONS AND MERCER THEOREM
• Theory of Reproducing Kernels
• Title not available (Why is that?)
• On early stopping in gradient descent learning
• On the mathematical foundations of learning
• Title not available (Why is that?)
• On the influence of the kernel on the consistency of support vector machines
• Title not available (Why is that?)
• Optimal aggregation of classifiers in statistical learning.
• Title not available (Why is that?)
• Learning theory estimates via integral operators and their approximations
• Theory of Classification: a Survey of Some Recent Advances
• Mercer theorem for RKHS on noncompact sets
• Model selection for regularized least-squares algorithm in learning theory
• Approximation in learning theory
• An Explicit Description of the Reproducing Kernel Hilbert Spaces of Gaussian RBF Kernels
• Learnability of Gaussians with flexible variances
• Generalization bounds for function approximation from scattered noisy data
• Reproducing kernel Hilbert spaces associated with analytic translation-invariant Mercer kernels

Cited In (58)

• Moduli of smoothness, \(K\)-functionals and Jackson-type inequalities associated with Kernel function approximation in learning theory
• Reproducing property of bounded linear operators and kernel regularized least square regressions
• On sufficient dimension reduction for functional data: inverse moment-based methods
• Global and local views of the Hilbert space associated to Gaussian kernel
• Gaussian kernel quadrature at scaled Gauss-Hermite nodes
• On the mathematical foundations of stable RKHSs
• Frames, reproducing kernels, regularization and learning
• Title not available (Why is that?)
• On the positivity and magnitudes of Bayesian quadrature weights
• Worst-case optimal approximation with increasingly flat Gaussian kernels
• An approach to the Gaussian RBF kernels via Fock spaces
• Efficient kernel canonical correlation analysis using Nyström approximation
• Learning rates for classification with Gaussian kernels
• Support vector machine adapted Tikhonov regularization method to solve Dirichlet problem
• Covering numbers of Gaussian reproducing kernel Hilbert spaces
• Orthonormal expansions for translation-invariant kernels
• A least square point of view to reproducing kernel methods to solve functional equations
• Low-rank kernel approximation of Lyapunov functions using neural networks
• Sparsity-promoting algorithms for the discovery of informative Koopman-invariant subspaces
• Derivative reproducing properties for kernel methods in learning theory
• Reproducing properties of differentiable Mercer-like kernels on the sphere
• On Gaussian kernels on Hilbert spaces and kernels on hyperbolic spaces
• Inference on the reproducing kernel Hilbert spaces
• Linear and nonlinear approximation of spherical radial basis function networks
• Integration in reproducing kernel Hilbert spaces of Gaussian kernels
• Statistical properties of the method of regularization with periodic Gaussian reproducing kernel
• Nonparametric regression using needlet kernels for spherical data
• Kolmogorov widths on the sphere via eigenvalue estimates for Hölderian integral operators
• Finite Sample Approximations of Exact and Entropic Wasserstein Distances Between Covariance Operators and Gaussian Processes
• Asymptotic distribution for regression in a symmetric periodic Gaussian kernel Hilbert space
• Determinantal Point Processes Implicitly Regularize Semiparametric Regression Problems
• On a nonlinear extension of the principal fitted component model
• Kernel-based interpolation at approximate Fekete points
• Reproducing kernels in probability and statistics
• Learnability in Hilbert spaces with reproducing kernels
• Comparing fixed and variable-width Gaussian networks
• Approximation properties of certain operator-induced norms on Hilbert spaces
• Ensemble forecasts in reproducing kernel Hilbert space family
• p-kernel Stein variational gradient descent for data assimilation and history matching
• Stochastic saddle-point optimization for the Wasserstein barycenter problem
• The Gaussian Radon transform and machine learning
• Title not available (Why is that?)
• Interpolation and best approximation for spherical radial basis function networks
• On the Use of Reproducing Kernel Hilbert Spaces in Functional Classification
• Approximating and learning by Lipschitz kernel on the sphere
• Learning from non-random data in Hilbert spaces: an optimal recovery perspective
• From covariance matrices to covariance operators: data representation from finite to infinite-dimensional settings
• Learning with centered reproducing kernels
• The regularized least squares algorithm and the problem of learning halfspaces
• Geometric measures and properties of commonly used kernel functions
• Learning rates of regularized regression on the unit sphere
• Nonlinear and additive principal component analysis for functional data
• Small sample spaces for Gaussian processes
• Approximation of reachable sets using optimal control and support vector machines
• Learning Rates of l^q Coefficient Regularization Learning with Gaussian Kernel
• On a collocation point of view to reproducing kernel methods
• An Explicit Description of the Reproducing Kernel Hilbert Spaces of Gaussian RBF Kernels
• Regularized Nyström Subsampling in Covariate Shift Domain Adaptation Problems

This page was built for publication: Some properties of Gaussian reproducing kernel Hilbert spaces and their implications for function approximation and learning theory

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5962345)