Projection-based approximation and a duality with kernel methods

DOI10.1214/AOS/1176347004MaRDI QIDQ913418zbMATH OpenOpenAlexFDO

Authors David Donoho, Iain M. Johnstone

Publication date 1989

Published in The Annals of Statistics (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1214/aos/1176347004

zbMATH Keywords

kernel regressionconvergencecurse of dimensionalitydimensionality reductionapproximationharmonic functionsHermite polynomialsLaplaciansmoothnessGaussian measureradial functionsnoisy datalocal averagingtwo-dimensional problemangular smoothnessL2-approximation errorminimax rate ofProjection pursuit regressionrates of

Mathematics Subject Classification ID

Multivariate analysis (62H99) General nonlinear regression (62J02) Nonparametric inference (62G99) Approximation by polynomials (41A10) Fourier series in special orthogonal functions (Legendre polynomials, Walsh functions, etc.) (42C10) Rate of convergence, degree of approximation (41A25)

Recommendations

• On projection pursuit regression
• scientific article; zbMATH DE number 4028654
• The \(L_p\) convergence for projection pursuit regression
• Generalized projection pursuit regression
• Projection pursuit

Cited in

(32)

• L₂Version Of The Double Kernel Method
• Application of projection pursuit learning to boundary detection and deblurring in images
• Distribution-specific hardness of learning neural networks
• scientific article; zbMATH DE number 4028654 (Why is no real title available?)
• USING THE MUTUAL INFORMATION COEFFICIENT TO IDENTIFY LAGS IN NONLINEAR MODELS
• Universal approximation by hierarchical fuzzy systems
• Learning non-parametric basis independent models from point queries via low-rank methods
• On using prototype reduction schemes to optimize kernel-based nonlinear subspace methods.
• On Kolmogorov's representation of functions of several variables by functions of one variable
• On the error of approximation by ridge functions with two fixed directions
• Nonlinear black-box models in system identification: Mathematical foundations
• A note on universal approximation by hierarchical fuzzy systems
• Data-independent random projections from the feature-map of the homogeneous polynomial kernel of degree two
• Probabilistic partition of unity networks for high‐dimensional regression problems
• Approximation of curve-based sleeve functions in high dimensions
• Nonparametric estimation when data on derivatives are available
• Gibbs sampling, exponential families and orthogonal polynomials
• Identifying linear combinations of ridge functions
• Relative efficiencies of model robust estimators in two-dimensional situations
• On the representability of a continuous multivariate function by sums of ridge functions
• Ridgelets: estimating with ridge functions
• Some problems in the theory of ridge functions
• Approximation by sums of ridge functions with fixed directions
• On a smoothness problem in ridge function representation
• Comparing Methods for Multivariate Nonparametric Regression
• A representation problem for smooth sums of ridge functions
• Linear and nonlinear methods of relief approximation
• On function recovery by neural networks based on orthogonal expansions
• Characterization of an extremal sum of ridge functions
• Dual bases and discrete reproducing kernels: a unified framework for RBF and MLS approximation
• A note on continuous sums of ridge functions
• Linearized two-layers neural networks in high dimension

This page was built for publication: Projection-based approximation and a duality with kernel methods

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q913418)