Learning a function from noisy samples at a finite sparse set of points
The paper deals with the task to learn a function \(f\) defined on a domain \(\Omega\) if only the values at a sparse, discrete subset \(\omega\subset\Omega\) are available. In the process of generalizing this given information, a generalization error occurs. It is the aim of the paper to estimate the bounds of this error under restrictions which are fulfilled in many cases. In the appendix, two ways which meet the assumptions are discussed. The results are developed using a bound on the generalization error basing on the Koksma-Hlawka type. It is shown that the generalization error has a deterministic bound and tends to zero ``if the noise in the measurement tends to zero and the number of sampling points tends to infinity sufficiently fast.
- Generalization bounds for function approximation from scattered noisy data
- Shannon sampling. II: Connections to learning theory
- A deterministic learning approach based on discrepancy.
- Learning general sparse additive models from point queries in high dimensions
- Deterministic error bounds for kernel-based learning techniques under bounded noise
- A simple lemma on greedy approximation in Hilbert space and convergence rates for projection pursuit regression and neural network training
- Approximation in learning theory
- Approximation methods for supervised learning
- Asymptotic Theory of Filtering for Linear Operator Equations with Discrete Noisy Data
- Bounds for the weighted L^p discrepancy and tractability of integration
- Comparisons of parameter choice methods for regularization with discrete noisy data
- Consistency and rates of convergence of nonlinear Tikhonov regularization with random noise
- Convergence Rates of Approximate Least Squares Solutions of Linear Integral and Operator Equations of the First Kind
- Equivalent Norms for Sobolev Spaces
- Error bounds for approximation with neural networks
- Generalization bounds for function approximation from scattered noisy data
- scientific article; zbMATH DE number 53679 (Why is no real title available?)
- scientific article; zbMATH DE number 1049042 (Why is no real title available?)
- scientific article; zbMATH DE number 936298 (Why is no real title available?)
- scientific article; zbMATH DE number 3360568 (Why is no real title available?)
- Nonlinear function approximation: computing smooth solutions with an adaptive greedy algorithm
- Nonlinear methods of approximation
- On the mathematical foundations of learning
- On tractability of weighted integration over bounded and unbounded regions in ℝ^{𝕤}
- Rates of convex approximation in non-Hilbert spaces
- Regularization networks and support vector machines
- Regularized data-driven construction of fuzzy controllers
- Regularized greedy algorithms for network training with data noise
- Shannon sampling and function reconstruction from point values
- Some applications of multidimensional integration by parts
- Theory of Reproducing Kernels
- Universal approximation bounds for superpositions of a sigmoidal function
- Weighted Interpolation Inequalities of Sum and Product form in R n
- Weighted Sobolev interpolation inequalities on product spaces
- When are quasi-Monte Carlo algorithms efficient for high dimensional integrals?
- Über die Diskrepanz mehrdimensionaler Folgen mod 1
- Generalization bounds for function approximation from scattered noisy data
- The weight-decay technique in learning from data: an optimization point of view
- Deterministic error bounds for kernel-based learning techniques under bounded noise
- A deterministic learning approach based on discrepancy.
- Deterministic error analysis of kernel regularized regression for spherical scattered data
- Nonlinear function approximation: computing smooth solutions with an adaptive greedy algorithm
This page was built for publication: Learning a function from noisy samples at a finite sparse set of points
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1048968)
