Eignets for function approximation on manifolds

DOI10.1016/J.ACHA.2009.08.006MaRDI QIDQ984660zbMATHOpenAlexFDO

Authors H. N. Mhaskar

Publication date 20 July 2010

Published in Applied and Computational Harmonic Analysis (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/0909.5000

zbMATH Keywords

simultaneous approximationstability estimatesRBF networksdata dependent manifoldsdirect and converse theorems of approximationkernel based approximation

Mathematics Subject Classification ID

Computational difficulty of problems (lower bounds, completeness, difficulty of approximation, etc.) (68Q17) Approximation by other special function classes (41A30)

Abstract: Let $XX$ be a compact, smooth, connected, Riemannian manifold without boundary, $G:XXimesXXoRR$ be a kernel. Analogous to a radial basis function network, an eignet is an expression of the form $su{m}_{j=1}^M{a}_{j}G(circ,y_j)$, where $a_{j}inRR$, $y_{j}inXX$, $1lejleM$. We describe a deterministic, universal algorithm for constructing an eignet for approximating functions in $L^p(mu;XX)$ for a general class of measures $mu$ and kernels $G$. Our algorithm yields linear operators. Using the minimal separation amongst the centers $y_j$ as the cost of approximation, we give modulus of smoothness estimates for the degree of approximation by our eignets, and show by means of a converse theorem that these are the best possible for every emph{individual function}. We also give estimates on the coefficients $a_j$ in terms of the norm of the eignet. Finally, we demonstrate that if any sequence of eignets satisfies the optimal estimates for the degree of approximation of a smooth function, measured in terms of the minimal separation, then the derivatives of the eignets also approximate the corresponding derivatives of the target function in an optimal manner.

Recommendations

• Kernel Approximation on Manifolds I: Bounding the Lebesgue Constant
• scientific article; zbMATH DE number 2065335
• A direct approach for function approximation on data defined manifolds
• SPLINE APPROXIMATIONS ON MANIFOLDS
• Approximation of eigenfunctions in kernel-based spaces

Cites work

• scientific article; zbMATH DE number 3536702 (Why is no real title available?)
• scientific article; zbMATH DE number 3572640 (Why is no real title available?)
• scientific article; zbMATH DE number 477682 (Why is no real title available?)
• scientific article; zbMATH DE number 1368940 (Why is no real title available?)
• scientific article; zbMATH DE number 823880 (Why is no real title available?)
• scientific article; zbMATH DE number 2196447 (Why is no real title available?)
• A quadrature formula for diffusion polynomials corresponding to a generalized heat kernel
• A walk through energy, discrepancy, numerical integration and group invariant measures on measurable subsets of Euclidean space
• Data analysis and representation on a general domain using eigenfunctions of Laplacian
• Derivatives of the spectral function and Sobolev norms of eigenfunctions on a closed Riemannian manifold
• Diffusion polynomial frames on metric measure spaces
• Diffusion wavelets
• Efficient reconstruction of functions on the sphere from scattered data
• From graph to manifold Laplacian: the convergence rate
• Image manifolds which are isometric to Euclidean space
• Local Paley–Wiener theorems for functions analytic on unit spheres
• Localized linear polynomial operators and quadrature formulas on the sphere
• Polynomial approximation on the sphere using scattered data
• Semi-supervised learning on Riemannian manifolds
• Some Properties of the Eigenfunctions of The Laplace-Operator on Riemannian Manifolds
• The spectral function of an elliptic operator
• Towards a theoretical foundation for Laplacian-based manifold methods
• Universal local parametrizations via heat kernels and eigenfunctions of the Laplacian
• When is approximation by Gaussian networks necessarily a linear process?
• \(L^ p\)-theory of elliptic differential operators on manifolds of bounded geometry

Cited in

(33)

• Smooth function extension based on high dimensional unstructured data
• Minimum Sobolev norm interpolation with trigonometric polynomials on the torus
• Construction and Monte Carlo estimation of wavelet frames generated by a reproducing kernel
• Representation of functions on big data associated with directed graphs
• Function approximation with zonal function networks with activation functions analogous to the rectified linear unit functions
• Dual framelets transform on manifolds and graphs
• A generalized diffusion frame for parsimonious representation of functions on data defined manifolds
• A unified framework for harmonic analysis of functions on directed graphs and changing data
• Applied harmonic analysis and data processing. Abstracts from the workshop held March 25--31, 2018
• Metric entropy, \(n\)-widths, and sampling of functions on manifolds
• A direct approach for function approximation on data defined manifolds
• Data Based Construction of Kernels for Classification
• Tight framelets and fast framelet filter bank transforms on manifolds
• Band-limited localized Parseval frames and Besov spaces on compact homogeneous manifolds
• Quasi Monte Carlo Integration and Kernel-Based Function Approximation on Grassmannians
• Deep neural networks can stably solve high-dimensional, noisy, non-linear inverse problems
• scientific article; zbMATH DE number 7625171 (Why is no real title available?)
• Super-resolution meets machine learning: approximation of measures
• An analysis of training and generalization errors in shallow and deep networks
• \(\varepsilon\)-coverings of Hölder-Zygmund type spaces on data-defined manifolds
• Applications of classical approximation theory to periodic basis function networks and computational harmonic analysis
• Function recovery on manifolds using scattered data
• Local approximation using Hermite functions
• Representation of functions on big data: graphs and trees
• Approximate Quadrature Measures on Data-Defined Spaces
• Approximation by linear combinations of translates of a single function
• Minimum Sobolev norm interpolation of scattered derivative data
• Weighted least \(\ell_p\) approximation on compact Riemannian manifolds
• Regularized kernel-based reconstruction in generalized Besov spaces
• Marcinkiewicz-Zygmund measures on manifolds
• Function approximation by deep networks
• Estimation of a regression function on a manifold by fully connected deep neural networks
• Curve based approximation of measures on manifolds by discrepancy minimization

This page was built for publication: Eignets for function approximation on manifolds

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q984660)