Capturing ridge functions in high dimensions from point queries

DOI10.1007/s00365-011-9147-6zbMath1318.62286OpenAlexW1991143958MaRDI QIDQ2428577

Ronald A. DeVore, Gérard Kerkyacharian, Dominique Picard, Ingrid Daubechies, Albert Cohen

Publication date: 26 April 2012

Published in: Constructive Approximation (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s00365-011-9147-6

zbMATH Keywords

ridge functionshigh-dimensional interpolationactive learningcompressed sensing

Mathematics Subject Classification ID

Nonparametric regression and quantile regression (62G08) Signal theory (characterization, reconstruction, filtering, etc.) (94A12) Numerical interpolation (65D05) Neural nets and related approaches to inference from stochastic processes (62M45)

Related Items (22)

A Survey of Compressed Sensing ⋮ Certified dimension reduction in nonlinear Bayesian inverse problems ⋮ Approximation of curve-based sleeve functions in high dimensions ⋮ Complexity of approximation of functions of few variables in high dimensions ⋮ High-dimensional estimation with geometric constraints: Table 1. ⋮ Learning functions of few arbitrary linear parameters in high dimensions ⋮ The recovery of ridge functions on the hypercube suffers from the curse of dimensionality ⋮ Data-Driven Polynomial Ridge Approximation Using Variable Projection ⋮ Gelfand numbers related to structured sparsity and Besov space embeddings with small mixed smoothness ⋮ On recovery of regular ridge functions ⋮ Dimension Reduction via Gaussian Ridge Functions ⋮ Learning non-parametric basis independent models from point queries via low-rank methods ⋮ Entropy and sampling numbers of classes of ridge functions ⋮ Inverse regression for ridge recovery: a data-driven approach for parameter reduction in computer experiments ⋮ Gradient-Based Dimension Reduction of Multivariate Vector-Valued Functions ⋮ A near-stationary subspace for ridge approximation ⋮ Approximation of generalized ridge functions in high dimensions ⋮ Gaussian Quadrature and Polynomial Approximation for One-Dimensional Ridge Functions ⋮ Unnamed Item ⋮ On some aspects of approximation of ridge functions ⋮ Recovery of regular ridge functions on the ball ⋮ Robust and resource-efficient identification of two hidden layer neural networks

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Convergence rates of best \(N\)-term Galerkin approximations for a class of elliptic SPDEs
• The Gelfand widths of \(\ell_p\)-balls for \(0 < p \leq 1\)
• Approximation of functions of few variables in high dimensions
• Instance-optimality in probability with an \(\ell _1\)-minimization decoder
• Nonparametric estimation of composite functions
• A simple proof of the restricted isometry property for random matrices
• Estimating high-dimensional intervention effects from observational data
• Additive regression and other nonparametric models
• Optimal rates and adaptation in the single-index model using aggregation
• Diffusion wavelets
• Compressed sensing and best 𝑘-term approximation
• Sliced Inverse Regression for Dimension Reduction
• Laplacian Eigenmaps for Dimensionality Reduction and Data Representation
• Information-Theoretic Limits on Sparsity Recovery in the High-Dimensional and Noisy Setting
• Distilled Sensing: Adaptive Sampling for Sparse Detection and Estimation
• Stable signal recovery from incomplete and inaccurate measurements

This page was built for publication: Capturing ridge functions in high dimensions from point queries