Refinement of Operator-valued Reproducing Kernels

zbMATH Open1283.68310arXiv1102.1324MaRDI QIDQ5405111FDOQ5405111

Authors: Haizhang Zhang, Yuesheng Xu, Qinghui Zhang 

Publication date: 1 April 2014

Abstract: This paper studies the construction of a refinement kernel for a given operator-valued reproducing kernel such that the vector-valued reproducing kernel Hilbert space of the refinement kernel contains that of the given one as a subspace. The study is motivated from the need of updating the current operator-valued reproducing kernel in multi-task learning when underfitting or overfitting occurs. Numerical simulations confirm that the established refinement kernel method is able to meet this need. Various characterizations are provided based on feature maps and vector-valued integral representations of operator-valued reproducing kernels. Concrete examples of refining translation invariant and finite Hilbert-Schmidt operator-valued reproducing kernels are provided. Other examples include refinement of Hessian of scalar-valued translation-invariant kernels and transformation kernels. Existence and properties of operator-valued reproducing kernels preserved during the refinement process are also investigated.

Full work available at URL: https://arxiv.org/abs/1102.1324

Recommendations

• Operator-valued reproducing kernels and their application in approximation and statistical learning
• Operator inequalities in reproducing kernel Hilbert spaces
• Representation of operators by kernels
• Operator theoretical classification of reproducing kernel Hilbert spaces
• scientific article; zbMATH DE number 1419176
• Refinement of reproducing kernels
• scientific article; zbMATH DE number 1054531
• Operator equations and regularization of approximation problems in reproducing kernel Hilbert spaces
• Singular Value Decomposition of Operators on Reproducing Kernel Hilbert Spaces
• scientific article; zbMATH DE number 1668772

zbMATH Keywords

numerical experimentsembeddingrefinementtranslation invariant kernelsvector-valued reproducing kernel Hilbert spacesHilbert-Schmidt kernelsHessian of Gaussian kernelsoperator-valued reproducing kernels

Mathematics Subject Classification ID

Nonparametric regression and quantile regression (62G08) General nonlinear regression (62J02) Learning and adaptive systems in artificial intelligence (68T05) Linear operators in reproducing-kernel Hilbert spaces (including de Branges, de Branges-Rovnyak, and other structured spaces) (47B32)

Cited In (10)

• Title not available (Why is that?)
• Weighted \(p\)-regular kernels for reproducing kernel Hilbert spaces and Mercer theorem
• Nonuniform sampling, reproducing kernels, and the associated Hilbert spaces
• Refinable kernels
• Generalized Gramians: creating frame vectors in maximal subspaces
• Sparse machine learning in Banach spaces
• Reproducing kernel Hilbert spaces via sampling in discrete spaces
• Operator-valued positive definite kernels and differentiable universality
• Learning rates of multitask kernel methods
• Refinement of reproducing kernels

This page was built for publication: Refinement of Operator-valued Reproducing Kernels

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5405111)