Random approximants and neural networks
From MaRDI portal
Publication:1914798
Let \(D\) be a set with a probability measure \(\mu\), \(\mu(D)=1\), and let \(K\) be a compact subset of \(L_q(D,\mu)\), \(1\leq q<\infty\). For \(f\in L_q\), \(n=1,2,\dots\), let \(\rho_n(f,K)=\inf|f-g_n|_q\), where the infimum is taken over all \(g_n\) of the form \(g_n= \sum^n_{i=1}a_i\phi_i\), with arbitrary \(\phi_i\in K\) and \(a_i\in R\). It is shown that for \(f\in \text{conv}(\pm K)\), under some mild restrictions, \(\rho_n(f,K)\leq C_q\varepsilon_n(K)n^{-1/2}\), where \(\varepsilon_n(K)\to 0\) as \(n\to\infty\). This fact is used to estimate the errors of certain neural net approximations. For the latter, also the lower estimates of errors are given.
Recommendations
Cited in
(56)- Uniform approximation by neural networks
- Estimator selection in the Gaussian setting
- Information-theoretic determination of minimax rates of convergence
- Neural network operators: constructive interpolation of multivariate functions
- Some problems in the theory of ridge functions
- On best approximation of classes by radial functions
- Approximation by ridge function fields over compact sets
- A note on error bounds for approximation in inner product spaces
- Approximation rates for neural networks with general activation functions
- A selective overview of deep learning
- Nonlinear autoregressive sieve bootstrap based on extreme learning machines
- High-order approximation rates for shallow neural networks with cosine and \(\mathrm{ReLU}^k\) activation functions
- Uniform approximation rates and metric entropy of shallow neural networks
- Interpolation by neural network operators activated by ramp functions
- Convergence of a family of neural network operators of the Kantorovich type
- Estimates of covering numbers of convex sets with slowly decaying orthogonal subsets
- Nonparametric neural network estimation of Lyapunov exponents and a direct test for chaos
- Properties of the neural network sieve bootstrap
- scientific article; zbMATH DE number 7038932 (Why is no real title available?)
- scientific article; zbMATH DE number 5164426 (Why is no real title available?)
- Minimization of Error Functionals over Perceptron Networks
- Regularization techniques and suboptimal solutions to optimization problems in learning from data
- Designing neural networks for modeling biological data: a statistical perspective
- Random interactions in higher order neural networks
- scientific article; zbMATH DE number 1303678 (Why is no real title available?)
- Multivariate neural network operators with sigmoidal activation functions
- On Random Matrices Arising in Deep Neural Networks. Gaussian Case
- scientific article; zbMATH DE number 7625172 (Why is no real title available?)
- Finite neuron method and convergence analysis
- RANDOM NEURAL NETWORK LEARNING HEURISTICS – CORRIGENDUM
- FAST NON-NEGATIVE LEAST-SQUARES LEARNING IN THE RANDOM NEURAL NETWORK
- Geometric Rates of Approximation by Neural Networks
- Some comparisons of complexity in dictionary-based and linear computational models
- scientific article; zbMATH DE number 2233617 (Why is no real title available?)
- A (semi)parametric functional coefficient logarithmic autoregressive conditional duration model
- Nonlinear approximation spaces for inverse problems
- Neural network approximation
- Estimation of the binary response model using a mixture of distributions estimator (MOD)
- An approximation result for nets in functional estimation
- On the approximation of functions by tanh neural networks
- Approximation capabilities of neural networks on unbounded domains
- Asymptotic properties of neural network sieve estimators
- Characterization of the variation spaces corresponding to shallow neural networks
- Fractional type multivariate neural network operators
- Causal inference of general treatment effects using neural networks with a diverging number of confounders
- Sharp Bounds on the Approximation Rates, Metric Entropy, and n-Widths of Shallow Neural Networks
- Optimal approximation of zonoids and uniform approximation by shallow neural networks
- Optimal rates of approximation by shallow \(\operatorname{ReLU}^k\) neural networks and applications to nonparametric regression
- Consistency and rate of convergence for deep ReLU neural networks
- Approximation error estimates by noise-injected neural networks
- A mixed residual method for biharmonic equations in spectral Barron spaces
- Sharp approximation rates for shallow ReLU neuralnetworks on critical Besov classes
- Classification with shallow neural networks
- Fully Deterministic Shallow Neural Networks with Localized Activations. Part I: Construction and Optimal Sobolev Approximation
- On the tractability of multivariate integration and approximation by neural networks
- Estimates of variation with respect to a set and applications to optimization problems
This page was built for publication: Random approximants and neural networks
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1914798)
