Entropy and sampling numbers of classes of ridge functions

DOI10.1007/s00365-014-9267-xzbMath1329.41043arXiv1311.2005OpenAlexW2138611516MaRDI QIDQ745852

Sebastian Mayer, Tino Ullrich, Jan Vybíral

Publication date: 14 October 2015

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

Full work available at URL: https://arxiv.org/abs/1311.2005

zbMATH Keywords

rate of convergencecurse of dimensionalityridge functionsinformation-based complexityentropy numberstractabilityweak tractabilitypolynomial tractabilitysampling approximationsampling numbers

Mathematics Subject Classification ID

Sobolev spaces and other spaces of ``smooth functions, embedding theorems, trace theorems (46E35) Best approximation, Chebyshev systems (41A50) Numerical interpolation (65D05) Multidimensional problems (41A63) Approximation by polynomials (41A10) Rate of convergence, degree of approximation (41A25) Algorithms for approximation of functions (65D15)

Related Items

Entropy numbers of functions on \([-1,1\) with Jacobi weights] ⋮ Counting Via Entropy: New Preasymptotics for the Approximation Numbers of Sobolev Embeddings ⋮ Approximation of curve-based sleeve functions in high dimensions ⋮ On the entropy numbers between the anisotropic spaces and the spaces of functions with mixed smoothness ⋮ The recovery of ridge functions on the hypercube suffers from the curse of dimensionality ⋮ Gelfand numbers related to structured sparsity and Besov space embeddings with small mixed smoothness ⋮ Tractability of the approximation of high-dimensional rank one tensors ⋮ On recovery of regular ridge functions ⋮ Gradient-Based Dimension Reduction of Multivariate Vector-Valued Functions ⋮ Gaussian Quadrature and Polynomial Approximation for One-Dimensional Ridge Functions ⋮ On some aspects of approximation of ridge functions ⋮ Stable recovery of entangled weights: towards robust identification of deep neural networks from minimal samples ⋮ 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
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Learning functions of few arbitrary linear parameters in high dimensions
• Entropy numbers of spheres in Banach and quasi-Banach spaces
• Statistics for high-dimensional data. Methods, theory and applications.
• The Gelfand widths of \(\ell_p\)-balls for \(0 < p \leq 1\)
• Infinite-dimensional quadrature and approximation of distributions
• Geometric properties of the ridge function manifold
• Function spaces in Lipschitz domains and optimal rates of convergence for sampling
• Tractability of multivariate problems. Volume I: Linear information
• Tractability of multivariate problems. Volume II: Standard information for functionals.
• Entropy numbers of diagonal operators between symmetric Banach spaces
• Optimal reconstruction of a function from its projections
• Identifying linear combinations of ridge functions
• Harmonic analysis of neural networks
• Asymptotic minimax estimation of regression in the additive model
• Direct estimation of the index coefficient in a single-index model
• Approximation of infinitely differentiable multivariate functions is intractable
• Capturing ridge functions in high dimensions from point queries
• Weak and quasi-polynomial tractability of approximation of infinitely differentiable functions
• The curse of dimensionality for numerical integration of smooth functions. II
• Sparse tensor discretizations of high-dimensional parametric and stochastic PDEs
• Learning Theory
• Lower bounds for constant weight codes
• Ridgelets: a key to higher-dimensional intermittency?
• Minimax-optimal rates for sparse additive models over kernel classes via convex programming
• A lower estimate for entropy numbers
• The elements of statistical learning. Data mining, inference, and prediction