Weighted quadrature formulas and approximation by zonal function networks on the sphere

DOI10.1016/j.jco.2005.10.003zbMath1103.65028MaRDI QIDQ2496179

Hrushikesh N. Mhaskar

Publication date: 12 July 2006

Published in: Journal of Complexity (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.jco.2005.10.003

zbMATH Keywords

neural networks; error bounds; radial basis functions; quadrature formulas; spherical basis functions; approximation on the sphere

Mathematics Subject Classification ID

41A55: Approximate quadratures

65D32: Numerical quadrature and cubature formulas

Related Items

OPTIMAL LOWER ESTIMATES FOR THE WORST CASE CUBATURE ERROR AND THE APPROXIMATION BY HYPERINTERPOLATION OPERATORS IN THE SOBOLEV SPACE SETTING ON THE SPHERE, Numerical integration with polynomial exactness over a spherical cap, Minimum Sobolev norm interpolation with trigonometric polynomials on the torus, Sufficient conditions for sampling and interpolation on the sphere, Needlet approximation for isotropic random fields on the sphere, Filtered hyperinterpolation: a constructive polynomial approximation on the sphere, Paley-Wiener approximations and multiscale approximations in Sobolev and Besov spaces on manifolds, Jackson-type inequalities for spherical neural networks with doubling weights, Optimal recovery of Besov classes of generalized smoothness and Sobolev classes on the sphere, The convergence rate for a \(K\)-functional in learning theory, Applied harmonic analysis and data processing. Abstracts from the workshop held March 25--31, 2018, Function approximation with zonal function networks with activation functions analogous to the rectified linear unit functions, Complexity estimates based on integral transforms induced by computational units, Essential rate for approximation by spherical neural networks, Fully discrete needlet approximation on the sphere, On filtered polynomial approximation on the sphere, Quadrature in Besov spaces on the Euclidean sphere, Polynomial operators and local approximation of solutions of pseudo-differential equations on the sphere, Polynomial operators for spectral approximation of piecewise analytic functions, Deep vs. shallow networks: An approximation theory perspective, $L^p$ Bernstein estimates and approximation by spherical basis functions

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Polynomial operators and local smoothness classes on the unit interval
• Numerical integration over spheres of arbitrary dimension
• On the tractability of multivariate integration and approximation by neural networks
• Computing Fourier transforms and convolutions on the 2-sphere
• Approximation of smooth functions on compact two-point homogeneous spaces
• On the representation of smooth functions on the sphere using finitely many bits
• Kolmogorov width of classes of smooth functions on the sphere \(\mathbb S^{d-1}\)
• Approximation properties of zonal function networks using scattered data on the sphere
• Polynomial operators and local approximation of solutions of pseudo-differential equations on the sphere
• A lower bound for the worst-case cubature error on spheres of arbitrary dimension
• Spherical harmonics
• A class of orthogonal polynomials
• Optimal lower bounds for cubature error on the sphere \(S^2\)
• Spherical Marcinkiewicz-Zygmund inequalities and positive quadrature
• Localized Tight Frames on Spheres
• Fast algorithms for discrete polynomial transforms
• Approximation by Ridge Functions and Neural Networks
• Universal approximation bounds for superpositions of a sigmoidal function
• Bounds on rates of variable-basis and neural-network approximation
• Scattered Data Interpolation on Spheres: Error Estimates and Locally Supported Basis Functions
• On generalized hyperinterpolation on the sphere
• Scattered Data Approximation