Distributed learning via filtered hyperinterpolation on manifolds
From MaRDI portal
Publication:2162123
Recommendations
- Distributed filtered hyperinterpolation for noisy data on the sphere
- Radial basis function approximation with distributively stored data on spheres
- Learning theory and approximation. Abstracts from the workshop held June 24--30, 2012.
- Approximation of functions on manifolds in high dimension from noisy scattered data
- Approximation of functions over manifolds: a moving least-squares approach
Cites work
- A distribution-free theory of nonparametric regression
- An encyclopaedia of cubature formulas.
- Analysis of framelet transforms on a simplex
- Approximation properties of zonal function networks using scattered data on the sphere
- Approximation theory and approximation practice
- Approximation Theory and Harmonic Analysis on Spheres and Balls
- Approximation with polynomial kernels and SVM classifiers
- Compactly supported positive definite radial functions
- Cubature over the sphere \(S^{2}\) in Sobolev spaces of arbitrary order
- Diffusion polynomial frames on metric measure spaces
- Discrete geometric analysis
- Distributed kernel-based gradient descent algorithms
- Distributed learning with regularized least squares
- Efficient spherical designs with good geometric properties
- Filtered hyperinterpolation: a constructive polynomial approximation on the sphere
- Filtered polynomial approximation on the sphere. (Abstract of thesis)
- Fourier series and approximation on hexagonal and triangular domains
- Fully discrete needlet approximation on the sphere
- scientific article; zbMATH DE number 1179494 (Why is no real title available?)
- Interpolation in polynomial classes and Markoff's inequality
- Learning theory of distributed spectral algorithms
- Localized linear polynomial operators and quadrature formulas on the sphere
- Localized Tight Frames on Spheres
- Marcinkiewicz-Zygmund measures on manifolds
- Numerical integration on the sphere
- ON APPROXIMATION OF FUNCTIONS ON THE SPHERE
- On filtered polynomial approximation on the sphere
- On generalized hyperinterpolation on the sphere
- On the mathematical foundations of learning
- Optimal asymptotic bounds for designs on manifolds
- Optimal asymptotic bounds for spherical designs
- Optimal recovery of Besov classes of generalized smoothness and Sobolev classes on the sphere
- Piecewise polynomial, positive definite and compactly supported radial functions of minimal degree
- Polynomial approximation on spheres -- generalizing de la Vallée-Poussin
- Polynomial interpolation and hyperinterpolation over general regions
- Quadrature rules and distribution of points on manifolds
- Quasi Monte Carlo Integration and Kernel-Based Function Approximation on Grassmannians
- Riemann localisation on the sphere
- Spherical codes and designs
- Spherical Marcinkiewicz-Zygmund inequalities and positive quadrature
- SVM Soft Margin Classifiers: Linear Programming versus Quadratic Programming
- The covering number in learning theory
- Tight framelets and fast framelet filter bank transforms on manifolds
Cited in
(7)- Distributed Learning via Filtered Hyperinterpolation on Manifolds
- Radial basis function approximation with distributively stored data on spheres
- Weighted least \(\ell_p\) approximation on compact Riemannian manifolds
- Hybrid hyperinterpolation over general regions
- A novel Riemannian conjugate gradient method with iteration complexity guarantees
- Spherical analysis of learning nonlinear functionals
- Monte Carlo quasi-interpolation of spherical data
This page was built for publication: Distributed learning via filtered hyperinterpolation on manifolds
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2162123)
