Moduli of smoothness, K-functionals and Jackson-type inequalities associated with Kernel function approximation in learning theory
The authors give investigations on a kernel function approximation problem arising from learning theory and show the convergence rate from the view of classical Fourier analysis. The paper is organized as follows: Section 1 contains the motivations for the tasks under consideration.\N\NIn Section 2, the authors provide some general notions and propositions for kernel function approximations, for example, \(K\)-functionals and moduli of smoothness and a Jackson-type inequality.\N\NIn Section 3, the authors apply the general theory and results of Section 2 to some concrete kernel function spaces, which include the kernel function spaces defined on the unit sphere, the kernel function spaces defined on the unit ball, the kernel function spaces defined on a mixed domain by both the unit sphere and the unit ball, and the kernel function spaces defined on a simplex.\N\NIn Section 4, the authors apply the Jackson inequalities established in Sections 2 and 3 to learning theory and express the learning rates.\N\NIn Section 5, the authors give some analysis and explanations of this paper, which contain five sections. The relationship between a modulus of smoothness and the heat kernel is stated in Section 5.1. The authors show a view point that, in some concrete kernel function spaces, the RKHS approximation may be sum up to kernel convolutional approximation. In Section 5.2, the authors provide some properties of Jackson inequality. The authors show that there is a family of radial kernel functions whose best approximation error cannot be described with the classical moduli of smoothness. In Section 5.3, the authors provide the problem of deep RKHS approximation. In Section 5.4, the authors give some comments on the advantages of this paper. In Section 5.5, the authors give explicit expressions for some moduli of smoothness and reproducing kernels with convolutional operators.
- On the K-functional in learning theory
- The convergence rate for a \(K\)-functional in learning theory
- On a generalized convolution approximation problem
- Approximation by families of generalized sampling series, realizations of generalized \(\mathcal{K} \)-functionals and generalized moduli of smoothness
- Density problem and approximation error in learning theory
- A note on application of integral operator in learning theory
- An Explicit Description of the Reproducing Kernel Hilbert Spaces of Gaussian RBF Kernels
- Analysis of regularized Nyström subsampling for regression functions of low smoothness
- Application of integral operator for regularized least-square regression
- Approximation in Sobolev spaces by kernel expansions
- Approximation numbers of Sobolev and Gevrey type embeddings on the sphere and on the ball -- preasymptotics, asymptotics, and tractability
- Approximation of eigenfunctions in kernel-based spaces
- Approximation of functions on the Sobolev space on the sphere in the average case setting
- Approximation Theory and Harmonic Analysis on Spheres and Balls
- Behavior of a functional in learning theory
- Best approximation of functions on the ball on the weighted Sobolev space equipped with a Gaussian measure
- Best choices for regularization parameters in learning theory: on the bias-variance problem.
- Best polynomial approximation on the unit sphere and the unit ball
- Characterization of Sobolev spaces on the sphere
- Complexity of numerical integration over spherical caps in a Sobolev space setting
- Convergence analysis of distributed multi-penalty regularized pairwise learning
- Deep distributed convolutional neural networks: universality
- Density problem and approximation error in learning theory
- ESTIMATING THE APPROXIMATION ERROR IN LEARNING THEORY
- Fourier series of Jacobi-Sobolev polynomials
- Fractional derivatives and best approximations
- Gaussian bounds for the heat kernels on the ball and the simplex: classical approach
- Gaussian bounds for the weighted heat kernels on the interval, ball, and simplex
- Generalized translation operator and approximation in several variables
- scientific article; zbMATH DE number 4090083 (Why is no real title available?)
- scientific article; zbMATH DE number 2171466 (Why is no real title available?)
- scientific article; zbMATH DE number 1862450 (Why is no real title available?)
- scientific article; zbMATH DE number 1889798 (Why is no real title available?)
- scientific article; zbMATH DE number 7626805 (Why is no real title available?)
- scientific article; zbMATH DE number 3263592 (Why is no real title available?)
- Kernel Approximation on Manifolds I: Bounding the Lebesgue Constant
- Kernel approximation on manifolds. II: The \(L_{\infty}\) norm of the \(L_2\) projector
- Kernel techniques: From machine learning to meshless methods
- Learning rates for regularized least squares ranking algorithm
- Learning rates for the kernel regularized regression with a differentiable strongly convex loss
- Learning rates for the risk of kernel-based quantile regression estimators in additive models
- Learning rates of least-square regularized regression
- Learning Theory
- Learning theory estimates via integral operators and their approximations
- Mercer theorem for RKHS on noncompact sets
- Mercer's theorem on general domains: on the interaction between measures, kernels, and RKHSs
- Multi-kernel regularized classifiers
- Neural network interpolation operators of multivariate functions
- New moduli of smoothness on the unit ball and other domains, introduction and main properties
- New moduli of smoothness on the unit ball, applications and computability
- Numerical integration over spheres of arbitrary dimension
- On approximation by reproducing kernel spaces in weighted L^p spaces
- On dimension-independent rates of convergence for function approximation with Gaussian kernels
- On regularization algorithms in learning theory
- On Sobolev orthogonal polynomials
- On the K-functional in learning theory
- On the density of translation networks defined on the unit ball
- On the mathematical foundations of learning
- Optimal learning with anisotropic Gaussian SVMs
- Optimal learning with Gaussians and correntropy loss
- Orthogonal polynomials and partial differential equations on the unit ball
- Polynomial approximation on polytopes
- Positive definiteness, reproducing kernel Hilbert spaces and beyond
- Probabilistic and average widths of Sobolev spaces on compact two-point homogeneous spaces equipped with a Gaussian measure
- Radial kernels and their reproducing kernel Hilbert spaces
- Rates of approximation by neural network interpolation operators
- Reproducing kernel Hilbert spaces associated with kernels on topological spaces
- Reproducing properties of differentiable Mercer-like kernels on the sphere
- Shannon sampling. II: Connections to learning theory
- Sobolev orthogonal polynomials defined via gradient on the unit ball
- Sobolev Orthogonal Polynomials on a Simplex
- Sobolev orthogonal polynomials on the unit ball via outward normal derivatives
- Some properties of Gaussian reproducing kernel Hilbert spaces and their implications for function approximation and learning theory
- Spectral approximation on the unit ball
- Spherical harmonics and approximations on the unit sphere. An introduction
- Strong converse inequalities
- Strong converse inequality for Poisson sums
- Summability of Fourier orthogonal series for Jacobi weight on a ball in ℝ^{𝕕}
- Support vector machine soft margin classifiers: error analysis
- The convergence rate for a \(K\)-functional in learning theory
- The convergence rate of a regularized ranking algorithm
- The kernel regularized learning algorithm for solving Laplace equation with Dirichlet boundary
- Theory of deep convolutional neural networks. II: Spherical analysis
- Theory of Reproducing Kernels
- Thresholded spectral algorithms for sparse approximations
- Weighted approximation of functions on the unit sphere
- Weighted Fourier-Laplace transforms in reproducing kernel Hilbert spaces on the sphere
- Weighted Sobolev orthogonal polynomials on the unit ball
- Widths of weighted Sobolev classes on the ball
- A new generalization of Szász-type operators involving Sheffer polynomials of class \(A^{(2)}\)
- Convex analysis method for distributed learning algorithm
- Hausdorff measure of noncompactness and Korovkin type approximation theorem for certain generalized difference sequence spaces
- General-Appell polynomials connecting Szász-Durrmeyer type operators and their approximation properties
- On the convergence rate of two-stage sampling distribution regression
- -Rescaled Pure Super Greedy Algorithm with respect to Riesz dictionary
This page was built for publication: Moduli of smoothness, \(K\)-functionals and Jackson-type inequalities associated with Kernel function approximation in learning theory
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6587592)
