Approximation with random bases: pro et contra
From MaRDI portal
Publication:2282874
Abstract: In this work we discuss the problem of selecting suitable approximators from families of parameterized elementary functions that are known to be dense in a Hilbert space of functions. We consider and analyze published procedures, both randomized and deterministic, for selecting elements from these families that have been shown to ensure the rate of convergence in norm of order , where is the number of elements. We show that both randomized and deterministic procedures are successful if additional information about the families of functions to be approximated is provided. In the absence of such additional information one may observe exponential growth of the number of terms needed to approximate the function and/or extreme sensitivity of the outcome of the approximation to parameters. Implications of our analysis for applications of neural networks in modeling and control are illustrated with examples.
Recommendations
- scientific article; zbMATH DE number 952958
- Approximation and randomness
- A characterization of random approximations
- scientific article; zbMATH DE number 515830
- Publication:5748356
- Random bit quadrature and approximation of distributions on Hilbert spaces
- scientific article; zbMATH DE number 1557032
- Some random approximation theorems with applications
- Approximation theory in random setting
- On realizations of an approximation random quadrature formula
Cites work
- A simple lemma on greedy approximation in Hilbert space and convergence rates for projection pursuit regression and neural network training
- Adaptation and Parameter Estimation in Systems With Unstable Target Dynamics and Nonlinear Parametrization
- Adaptation in the presence of a general nonlinear parameterization: an error model approach
- Adaptive control with nonconvex parameterization
- Approximation by superpositions of a sigmoidal function
- Approximation of continuous functions of several variables by an arbitrary nonlinear continuous function of one variable, linear functions, and their superpositions
- Approximation theory and approximation practice
- Fast decorrelated neural network ensembles with random weights
- Gamma function asymptotics by an extension of the method of steepest descents
- scientific article; zbMATH DE number 1149836 (Why is no real title available?)
- scientific article; zbMATH DE number 1392848 (Why is no real title available?)
- scientific article; zbMATH DE number 3231758 (Why is no real title available?)
- Is the \(k\)-NN classifier in high dimensions affected by the curse of dimensionality?
- Isoperimetry of waists and concentration of maps
- Metric structures for Riemannian and non-Riemannian spaces. Transl. from the French by Sean Michael Bates. With appendices by M. Katz, P. Pansu, and S. Semmes. Edited by J. LaFontaine and P. Pansu
- Near-Optimal Signal Recovery From Random Projections: Universal Encoding Strategies?
- Neural network control of nonlinear discrete-time systems.
- Neuro-Fuzzy Control of Industrial Systems with Actuator Nonlinearities
- On the applicability conditions for the algorithms of adaptive control in nonconvex problems
- Proportional concentration phenomena on the sphere
- Quasiorthogonal dimension of Euclidean spaces
- Universal approximation bounds for superpositions of a sigmoidal function
Cited in
(32)- Random approximants and neural networks
- Directed paths in random media, function approximation and nonlinear regression.
- Prescribed performance based model-free adaptive sliding mode constrained control for a class of nonlinear systems
- Correlations of random classifiers on large data sets
- Probabilistic lower bounds for approximation by shallow perceptron networks
- Correction of AI systems by linear discriminants: probabilistic foundations
- Randomized mixture models for probability density approximation and estimation
- One-trial correction of legacy AI systems and stochastic separation theorems
- High-dimensional brain: a tool for encoding and rapid learning of memories by single neurons
- Stochastic separation theorems
- Insights into randomized algorithms for neural networks: practical issues and common pitfalls
- scientific article; zbMATH DE number 1557032 (Why is no real title available?)
- The Behavior of Random Reduced Bases
- Blessing of dimensionality: mathematical foundations of the statistical physics of data
- Randomized multi-scale kernels learning with sparsity constraint regularization for regression
- Approximating unknown functions when fitting errors involve costs
- New Method to Determine Topology of Low-Dimension Manifold Approximating Multidimensional Data Sets
- Blessing of dimensionality at the edge and geometry of few-shot learning
- General stochastic separation theorems with optimal bounds
- Stochastic configuration networks with chaotic maps and hierarchical learning strategy
- Stochastic configuration networks for multi-dimensional integral evaluation
- A geometric view on the role of nonlinear feature maps in few-shot learning
- Sensitivity Analysis of the Neural Networks Randomized Learning
- Prediction of X-ray fluorescence copper grade using regularized stochastic configuration networks
- Approximation of classifiers by deep perceptron networks
- An improved stochastic configuration network for concentration prediction in wastewater treatment process
- Greedy deep stochastic configuration networks ensemble with boosting negative correlation learning
- RandONets: shallow networks with random projections for learning linear and nonlinear operators
- A resolution independent neural operator
- Random projection neural networks of best approximation: convergence theory and practical applications
- How neural networks work: unraveling the mystery of randomized neural networks for functions and chaotic dynamical systems
- Robust stochastic configuration networks with kernel density estimation for uncertain data regression
This page was built for publication: Approximation with random bases: pro et contra
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2282874)
