Positive definite dot product kernels in learning theory

DOI10.1007/s10444-004-3140-6zbMath1082.68097OpenAlexW2082500594MaRDI QIDQ1767054

Hongwei Sun, Fangyan Lu

Publication date: 4 March 2005

Published in: Advances in Computational Mathematics (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s10444-004-3140-6

zbMATH Keywords

positive definiteMercer kernelsconditionally positive definiteGramian positive functions

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Positive definite functions in one variable harmonic analysis (42A82) Interpolation in approximation theory (41A05)

Related Items

Sampling inequalities for infinitely smooth functions, with applications to interpolation and machine learning, Decay of Singular Values of Power Series Kernels on the Sphere, Nuclearity for power series kernels in higher dimensions, Rank restricting functions, Strictly positive definite kernels on subsets of the complex plane, On conditionally positive definite dot product kernels, Sharp estimates for eigenvalues of integral operators generated by dot product kernels on the sphere, Conditionally positive definite dot product kernels, Power series kernels, Positive definite matrix functions on spheres defined by hypergeometric functions, Density problem and approximation error in learning theory, Strictly Hermitian positive definite functions, Matrix-valued positive definite kernels given by expansions: strict positive definiteness

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Interpolation of scattered data: distance matrices and conditionally positive definite functions
• Constrained \(L_ p\) approximation
• Strictly positive definite functions on a real inner product space
• Best choices for regularization parameters in learning theory: on the bias-variance problem.
• The covering number in learning theory
• Functions that preserve families of positive semidefinite matrices
• Regularization networks and support vector machines
• On the mathematical foundations of learning
• 10.1162/153244302760185252
• Smoothing and Interpolation in a Convex Subset of a Hilbert Space
• Smoothing and interpolation in a convex subset of a Hilbert space : II. The semi-norm case
• ESTIMATING THE APPROXIMATION ERROR IN LEARNING THEORY
• Strictly positive definite kernels on the hilbert sphere
• What is the Laplace Transform?
• \(\ell\)-norm and its application to learning theory