A simple lemma on greedy approximation in Hilbert space and convergence rates for projection pursuit regression and neural network training
From MaRDI portal
Publication:1192997
DOI10.1214/aos/1176348546zbMath0746.62060OpenAlexW2044828368WikidataQ124997995 ScholiaQ124997995MaRDI QIDQ1192997
Publication date: 27 September 1992
Published in: The Annals of Statistics (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1214/aos/1176348546
Hilbert spaceneuronsridge functionsneural network trainingprojection pursuit regressioniterative sequencesestimates of the rate of convergencegeneral convergence criteriongreedy basis expansion
Related Items
A mathematical perspective of machine learning, Lower bounds for artificial neural network approximations: a proof that shallow neural networks fail to overcome the curse of dimensionality, Analysis of the rate of convergence of two regression estimates defined by neural features which are easy to implement, Greedy algorithms for prediction, Unnamed Item, Another look at statistical learning theory and regularization, Accuracy of suboptimal solutions to kernel principal component analysis, Estimates of covering numbers of convex sets with slowly decaying orthogonal subsets, Density estimation with stagewise optimization of the empirical risk, Rescaled pure greedy algorithm for Hilbert and Banach spaces, Rates of convex approximation in non-Hilbert spaces, Approximation Bounds for Some Sparse Kernel Regression Algorithms, A receding-horizon regulator for nonlinear systems and a neural approximation, A NONPARAMETRIC ESTIMATOR FOR THE COVARIANCE FUNCTION OF FUNCTIONAL DATA, A Sobolev-type upper bound for rates of approximation by linear combinations of Heaviside plane waves, Convergence and rate of convergence of some greedy algorithms in convex optimization, Uniform approximation rates and metric entropy of shallow neural networks, ReLU deep neural networks from the hierarchical basis perspective, Nonlinear function approximation: computing smooth solutions with an adaptive greedy algorithm, High-dimensional change-point estimation: combining filtering with convex optimization, Neural network with unbounded activation functions is universal approximator, GENERALIZED CELLULAR NEURAL NETWORKS (GCNNs) CONSTRUCTED USING PARTICLE SWARM OPTIMIZATION FOR SPATIO-TEMPORAL EVOLUTIONARY PATTERN IDENTIFICATION, A novel scrambling digital image watermark algorithm based on double transform domains, A note on error bounds for approximation in inner product spaces, Some remarks on greedy algorithms, Nonlinear approximation in finite-dimensional spaces, The convex geometry of linear inverse problems, Comparison of the convergence rate of pure greedy and orthogonal greedy algorithms, Restricted polynomial regression, Training Neural Networks as Learning Data-adaptive Kernels: Provable Representation and Approximation Benefits, Estimation of projection pursuit regression via alternating linearization, Characterization of the variation spaces corresponding to shallow neural networks, Degree of Approximation Results for Feedforward Networks Approximating Unknown Mappings and Their Derivatives, A survey on universal approximation and its limits in soft computing techniques., Complexity estimates based on integral transforms induced by computational units, Accuracy of approximations of solutions to Fredholm equations by kernel methods, Unnamed Item, Greedy training algorithms for neural networks and applications to PDEs, Approximation with neural networks activated by ramp sigmoids, Can dictionary-based computational models outperform the best linear ones?, Vector greedy algorithms, Approximation by finite mixtures of continuous density functions that vanish at infinity, Minimization of Error Functionals over Perceptron Networks, Greedy expansions with prescribed coefficients in Hilbert spaces, On \(n\)-term approximation with positive coefficients, Learning semidefinite regularizers, Approximation Properties of Ridge Functions and Extreme Learning Machines, Convergence properties of cascade correlation in function approximation., On function recovery by neural networks based on orthogonal expansions, Finite Neuron Method and Convergence Analysis, Approximation and learning by greedy algorithms, Schwarz iterative methods: infinite space splittings, Deviation optimal learning using greedy \(Q\)-aggregation, New insights into Witsenhausen's counterexample, Some extensions of radial basis functions and their applications in artificial intelligence, Regularized vector field learning with sparse approximation for mismatch removal, Estimates of variation with respect to a set and applications to optimization problems, Approximation of functions of finite variation by superpositions of a sigmoidal function., Some comparisons of complexity in dictionary-based and linear computational models, A note on a scale-sensitive dimension of linear bounded functionals in Banach spaces, Simultaneous greedy approximation in Banach spaces, Approximation on anisotropic Besov classes with mixed norms by standard information, Learning with generalization capability by kernel methods of bounded complexity, Regularized greedy algorithms for network training with data noise, Ridge functions and orthonormal ridgelets, Unnamed Item, Simultaneous approximation by greedy algorithms, An approximation result for nets in functional estimation, Unnamed Item, Approximation with random bases: pro et contra, Geometric Rates of Approximation by Neural Networks, Approximation by superpositions of a sigmoidal function, Complexity of Gaussian-radial-basis networks approximating smooth functions, Some problems in the theory of ridge functions, Insights into randomized algorithms for neural networks: practical issues and common pitfalls, Risk bounds for mixture density estimation, Boosting the margin: a new explanation for the effectiveness of voting methods, Models of knowing and the investigation of dynamical systems, Approximation schemes for functional optimization problems, A note on error bounds for function approximation using nonlinear networks, An Integral Upper Bound for Neural Network Approximation, Convergence analysis of convex incremental neural networks, On a greedy algorithm in the space \(L_p[0,1\)], Harmonic analysis of neural networks, Greedy algorithms and \(M\)-term approximation with regard to redundant dictionaries, A better approximation for balls, Information-theoretic determination of minimax rates of convergence, On simultaneous approximations by radial basis function neural networks, Scalable Semidefinite Programming, Joint Inversion of Multiple Observations, Learning a function from noisy samples at a finite sparse set of points, Functional aggregation for nonparametric regression., Local greedy approximation for nonlinear regression and neural network training., Unnamed Item, Generalized approximate weak greedy algorithms, Greedy approximation in convex optimization, Approximation properties of local bases assembled from neural network transfer functions, Boosting with early stopping: convergence and consistency, Rates of minimization of error functionals over Boolean variable-basis functions, Generalization bounds for sparse random feature expansions, High-order approximation rates for shallow neural networks with cosine and \(\mathrm{ReLU}^k\) activation functions, A New Function Space from Barron Class and Application to Neural Network Approximation
