Application of integral operator for regularized least-square regression

DOI10.1016/j.mcm.2008.08.005zbMath1165.45310OpenAlexW2033972076MaRDI QIDQ2389897

Qiang Wu, Hongwei Sun

Publication date: 20 July 2009

Published in: Mathematical and Computer Modelling (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.mcm.2008.08.005

zbMATH Keywords

consistencyintegral operatorreproducing kernel Hilbert spaceregularized least-square regression

Mathematics Subject Classification ID

Integral operators (45P05)

Related Items (23)

Coefficient regularized regression with non-iid sampling ⋮ Reproducing properties of differentiable Mercer-like kernels ⋮ LEAST SQUARE REGRESSION WITH COEFFICIENT REGULARIZATION BY GRADIENT DESCENT ⋮ Approximation of eigenfunctions in kernel-based spaces ⋮ Reproducing kernel Hilbert spaces associated with kernels on topological spaces ⋮ Regularized least square regression with unbounded and dependent sampling ⋮ An extension of Mercer's theory to \(L^p\) ⋮ Hierarchical least squares algorithms for single-input multiple-output systems based on the auxiliary model ⋮ Least square regression with indefinite kernels and coefficient regularization ⋮ Learning rates for the kernel regularized regression with a differentiable strongly convex loss ⋮ On the K-functional in learning theory ⋮ Optimality of regularized least squares ranking with imperfect kernels ⋮ Regression learning with non-identically and non-independently sampling ⋮ Learning performance of uncentered kernel-based principal component analysis ⋮ Consistency analysis of spectral regularization algorithms ⋮ Bias corrected regularization kernel method in ranking ⋮ Reproducing Properties of Differentiable Mercer-Like Kernels on the Sphere ⋮ Learning performance of regularized regression with multiscale kernels based on Markov observations ⋮ REGULARIZED LEAST SQUARE ALGORITHM WITH TWO KERNELS ⋮ The convergence rate of a regularized ranking algorithm ⋮ Debiased magnitude-preserving ranking: learning rate and bias characterization ⋮ Half supervised coefficient regularization for regression learning with unbounded sampling ⋮ Unnamed Item

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Mercer theorem for RKHS on noncompact sets
• Regularized least square regression with dependent samples
• Reproducing kernel Hilbert spaces associated with analytic translation-invariant Mercer kernels
• Best choices for regularization parameters in learning theory: on the bias-variance problem.
• The covering number in learning theory
• Learning rates of least-square regularized regression
• Shannon sampling. II: Connections to learning theory
• Learning theory estimates via integral operators and their approximations
• On the mathematical foundations of learning
• Capacity of reproducing kernel spaces in learning theory
• Scale-sensitive dimensions, uniform convergence, and learnability
• Shannon sampling and function reconstruction from point values
• 10.1162/153244303321897690
• Theory of Reproducing Kernels

This page was built for publication: Application of integral operator for regularized least-square regression