Learning rates of regularized regression on the unit sphere
From MaRDI portal
This paper studies least square regularized regression learning algorithms with spherical harmonics kernels on the unit sphere. The learning error is decomposed into sample error and regularized error. To estimate the regularized error, the best approximation operator and the Jackson-type inequality are introduced. The other interesting point is that the dimension of hypothesis space charges with the size of samples. Satisfying error bound and learning rate are deduced by the covering number technique.
Recommendations
- The learning rate for regularized least-squares algorithm on the unit sphere
- Regularized least square regression with spherical polynomial kernels
- Learning rates of least-square regularized regression
- Learning rates of least-square regularized regression with polynomial kernels
- Approximating and learning by Lipschitz kernel on the sphere
Cites work
- A Duchon framework for the sphere
- A modulus of smoothness on the unit sphere
- Approximation with polynomial kernels and SVM classifiers
- Direct and inverse Sobolev error estimates for scattered data interpolation via spherical basis functions
- ESTIMATING THE APPROXIMATION ERROR IN LEARNING THEORY
- scientific article; zbMATH DE number 1804115 (Why is no real title available?)
- scientific article; zbMATH DE number 1128580 (Why is no real title available?)
- Jackson-type inequality for doubling weights on the sphere
- Jackson-type inequality on the sphere
- Learning and approximation by Gaussians on Riemannian manifolds
- Learning rates of least-square regularized regression
- On the mathematical foundations of learning
- Regularized least square regression with spherical polynomial kernels
- Semi-supervised learning on Riemannian manifolds
- Shannon sampling and function reconstruction from point values
- Some properties of Gaussian reproducing kernel Hilbert spaces and their implications for function approximation and learning theory
- Spherical harmonics
- Support vector machine soft margin classifiers: error analysis
- Theory of Reproducing Kernels
- Universal kernels
Cited in
(11)- Nonparametric regression using needlet kernels for spherical data
- Learning rates of least-square regularized regression
- Approximating and learning by Lipschitz kernel on the sphere
- Complexity of Monte Carlo integration for Besov classes on the unit sphere
- The learning rate for regularized least-squares algorithm on the unit sphere
- Nonparametric Regression for Spherical Data
- The kernel regularized learning algorithm for solving Laplace equation with Dirichlet boundary
- Regularized least square regression with spherical polynomial kernels
- Reproducing property of bounded linear operators and kernel regularized least square regressions
- TSSS: a novel triangulated spherical spline smoothing for surface-based data
- Deterministic error analysis of kernel regularized regression for spherical scattered data
This page was built for publication: Learning rates of regularized regression on the unit sphere
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q365838)
