New duality in choices of feature spaces via kernel analysis

DOI10.1007/S43670-025-00099-ZMaRDI QIDQ6980460zbMATH OpenFDO

Authors Palle Jorgensen, Feng Tian

Publication date 22 May 2025

Published in Sampling Theory, Signal Processing, and Data Analysis (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/S43670-025-00099-Z

zbMATH Keywords

covariance kernelsembedding problemfactorizationfeature selectionfeature spaceGaussian processgeometrykernel optimizationoperator theoryoptimizationpositive-definite kernelprincipal component analysisreproducing kernel Hilbert spaceSchwartz distributions

Mathematics Subject Classification ID

Abstract approximation theory (approximation in normed linear spaces and other abstract spaces) (41A65) Positive definite functions in one variable harmonic analysis (42A82) General harmonic expansions, frames (42C15) Hilbert spaces with reproducing kernels (= (proper) functional Hilbert spaces, including de Branges-Rovnyak and other structured spaces) (46E22) Linear operators in reproducing-kernel Hilbert spaces (including de Branges, de Branges-Rovnyak, and other structured spaces) (47B32) Gaussian processes (60G15) Artificial neural networks and deep learning (68T07)

Cites work

• A class of optimal estimators for the covariance operator in reproducing kernel Hilbert spaces
• A Kaczmarz algorithm for sequences of projections, infinite products, and applications to frames in IFS \(L^2\) spaces
• A theorem of Beurling-Lax type for Hilbert spaces of functions analytic in the unit ball
• A topological characterization of a class of integral operators
• A topological view of unsupervised learning from noisy data
• An advanced complex analysis problem book. Topological vector spaces, functional analysis, and Hilbert spaces of analytic functions
• An Existence Theorem for Second Order Parabolic Equations
• An introduction to the theory of reproducing kernel Hilbert spaces
• Analytic reproducing kernels and multiplication operators
• Approximation properties of ridge functions and extreme learning machines
• Boundedness of the Segal-Bargmann transform on fractional Hermite-Sobolev spaces
• Bounds for analysic functions in domains with a distinguished boundary surface
• Choosing shape parameters for regression in reproducing kernel Hilbert space and variable selection
• Coherent states for the Manin plane via Toeplitz quantization
• Composition operators on Hilbert spaces of entire functions with analytic symbols
• Cross-Toeplitz operators on the Fock-Segal-Bargmann spaces and two-sided convolutions on the Heisenberg group
• Diagonalizing operators with reflection symmetry
• Dual pairs of operators, harmonic analysis of singular nonatomic measures and Krein-Feller diffusion
• Estimates for Green's functions of elliptic equations in non-divergence form with continuous coefficients
• Estimates on the Green's function of second-order elliptic operators in ℝ^N
• Green's functions for some highly degenerate elliptic operators
• Harmonic analysis of fractal measures: basis and frame algorithms for fractal \(L^2\)-spaces, and boundary representations as closed subspaces of the Hardy space
• Harmonic analysis of network systems via kernels and their boundary realizations
• scientific article; zbMATH DE number 3437485 (Why is no real title available?)
• Infinite-dimensional stochastic transforms and reproducing kernel Hilbert space
• Kernel functions and eigenfunction expansions
• Kernel methods in system identification, machine learning and function estimation: a survey
• Kernel-based data fusion for machine learning. Methods and applications in bioinformatics and text mining.
• Limitations of clustering with PCA and correlated noise
• Local Minimax Learning of Functions With Best Finite Sample Estimation Error Bounds: Applications to Ridge and Lasso Regression, Boosting, Tree Learning, Kernel Machines, and Inverse Problems
• Local receptive fields based extreme learning machine with hybrid filter kernels for image classification
• New characterizations of reproducing kernel Hilbert spaces and applications to metric geometry
• On the Bargmann-Fock-Fueter and Bergman-Fueter integral transforms
• On the extension of positive definite kernels to topological algebras
• Perturbed Hankel determinant, correlation functions and Painlevé equations
• Projection divergence in the reproducing kernel Hilbert space: asymptotic normality, block-wise and slicing estimation, and computational efficiency
• Propagating uncertainty through system dynamics in reproducing kernel Hilbert space
• Quantum dynamics of the classical harmonic oscillator
• Reflection positivity via Krein space analysis
• Representing systems of reproducing kernels in spaces of analytic functions
• Reproducing kernel Banach spaces for machine learning
• Reproducing Kernel Hilbert Spaces Cannot Contain all Continuous Functions on a Compact Metric Space
• Reproducing kernels and choices of associated feature spaces, in the form of \(L^2\)-spaces
• Sous-espaces d'espaces vectoriels topologiques et noyaux associés. (Noyaux reproduisants.)
• Statistical inference using regularized M-estimation in the reproducing kernel Hilbert space for handling missing data
• Stochastics and dynamics of fractals
• Subalgebras of \(C^*\)-algebras. III: Multivariable operator theory
• The generalized -complex on the Segal-Bargmann space
• The weighted Bergman space on a sector and a degenerate parabolic equation
• Theory of Reproducing Kernels
• Weighted Moore-Penrose inverses for dual matrices and its applications
• White noise space analysis and multiplicative change of measures

Cited in

(1)

• Use of operator defect identities in multi-channel signal plus residual-analysis via iterated products and telescoping energy-residuals: applications to kernels in machine learning

This page was built for publication: New duality in choices of feature spaces via kernel analysis

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6980460)