Eignets for function approximation on manifolds

DOI10.1016/j.acha.2009.08.006zbMath1201.41003arXiv0909.5000OpenAlexW2963072276MaRDI QIDQ984660

Hrushikesh 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 approximationRBF networksstability estimatesdata 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)

Related Items

Construction and Monte Carlo estimation of wavelet frames generated by a reproducing kernel, Smooth function extension based on high dimensional unstructured data, Representation of functions on big data associated with directed graphs, An analysis of training and generalization errors in shallow and deep networks, Local Approximation Using Hermite Functions, Metric entropy, \(n\)-widths, and sampling of functions on manifolds, Estimation of a regression function on a manifold by fully connected deep neural networks, Function approximation by deep networks, Data Based Construction of Kernels for Classification, Quasi Monte Carlo Integration and Kernel-Based Function Approximation on Grassmannians, Approximate Quadrature Measures on Data-Defined Spaces, Marcinkiewicz-Zygmund measures on manifolds, Minimum Sobolev norm interpolation with trigonometric polynomials on the torus, \(\varepsilon\)-coverings of Hölder-Zygmund type spaces on data-defined manifolds, 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, Applications of classical approximation theory to periodic basis function networks and computational harmonic analysis, A unified framework for harmonic analysis of functions on directed graphs and changing data, Unnamed Item, Regularized kernel-based reconstruction in generalized Besov spaces, Band-limited localized Parseval frames and Besov spaces on compact homogeneous manifolds, A generalized diffusion frame for parsimonious representation of functions on data defined manifolds, Minimum Sobolev norm interpolation of scattered derivative data, Tight framelets and fast framelet filter bank transforms on manifolds, A direct approach for function approximation on data defined manifolds, Curve based approximation of measures on manifolds by discrepancy minimization, Super-resolution meets machine learning: approximation of measures, Representation of functions on big data: graphs and trees, Deep neural networks can stably solve high-dimensional, noisy, non-linear inverse problems, Approximation by linear combinations of translates of a single function

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Semi-supervised learning on Riemannian manifolds
• Data analysis and representation on a general domain using eigenfunctions of Laplacian
• A walk through energy, discrepancy, numerical integration and group invariant measures on measurable subsets of Euclidean space
• Towards a theoretical foundation for Laplacian-based manifold methods
• \(L^ p\)-theory of elliptic differential operators on manifolds of bounded geometry
• When is approximation by Gaussian networks necessarily a linear process?
• Derivatives of the spectral function and Sobolev norms of eigenfunctions on a closed Riemannian manifold
• A quadrature formula for diffusion polynomials corresponding to a generalized heat kernel
• Efficient reconstruction of functions on the sphere from scattered data
• Diffusion polynomial frames on metric measure spaces
• Diffusion wavelets
• From graph to manifold Laplacian: the convergence rate
• The spectral function of an elliptic operator
• Image manifolds which are isometric to Euclidean space
• Local Paley–Wiener theorems for functions analytic on unit spheres
• Universal local parametrizations via heat kernels and eigenfunctions of the Laplacian
• Localized Linear Polynomial Operators and Quadrature Formulas on the Sphere
• Polynomial approximation on the sphere using scattered data
• Some Properties of the Eigenfunctions of The Laplace-Operator on Riemannian Manifolds