Optimizing Kernel Methods: A Unifying Variational Principle

DOI10.2307/1403693MaRDI QIDQ3990530zbMATH OpenOpenAlexFDO

Authors Boris Granovsky, Hans-Georg Müller

Publication date 28 June 1992

Published in International Statistical Review / Revue Internationale de Statistique (Search for Journal in Brave)

Full work available at URL https://doi.org/10.2307/1403693

zbMATH Keywords

Legendre polynomialsmodeHermite polynomialscurve estimationJacobi polynomialsvariational principleexplicit solutionsinflection pointorder of smoothnessoptimal kernel functionsminimum variance kernelanalytic kernel functionexplicit Hermite representationlimiting kernel functionlocations of extrema of higher order derivativespolynomials with compact support

Mathematics Subject Classification ID

Density estimation (62G07) Asymptotic properties of nonparametric inference (62G20)

Recommendations

• Publication:3033130
• Minimax kernels for nonparametric curve estimation
• Remarks on extremal problems in nonparametric curve estimation
• Smooth optimum kernel estimators of densities, regression curves and modes
• Optimal kernels

Cited in

(30)

• On kernel density derivative estimation
• Remarks on optimum kernels and optimum boundary kernels.
• Twicing local linear kernel regression smoothers
• On automatic boundary corrections
• Data-Driven Optimization: A Reproducing Kernel Hilbert Space Approach
• Bernstein polynomial of recursive regression estimation with censored data
• Kernel-based Methods for Bandit Convex Optimization
• Multivariate density estimation with general flat-top kernels of infinite order
• Kernel embedding based variational approach for low-dimensional approximation of dynamical systems
• Sparse estimation within Pearson's system, with an application to financial market risk
• scientific article; zbMATH DE number 4131454 (Why is no real title available?)
• Exact mean integrated squared error and bandwidth selection for kernel distribution function estimators
• Local regression distribution estimators
• EFFICIENCY OF LINEAR REGRESSION ESTIMATORS BASED ON PRESMOOTHING
• Hierarchies of higher order kernels
• Bias reduction in kernel density estimation via Lipschitz condition
• Kernels, pre-images and optimization
• Surface and function approximation with nonparametric regression
• Kernel-based methods for bandit convex optimization
• Bias reduction by transformed flat-top Fourier series estimator of density on compact support
• Asymptotic unbiased density estimators
• On higher order kernels
• Towards learning optimized kernels for complex Langevin
• Generalized jackknifing and higher order kernels
• Nonparametric density estimation for multivariate bounded data
• On optimal kernel choice for deconvolution
• Differences and derivatives in kernel estimation
• Adaptive bandwidth choice
• Reducing variance in nonparametric surface estimation
• Minimax kernels for nonparametric curve estimation

This page was built for publication: Optimizing Kernel Methods: A Unifying Variational Principle

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3990530)