Approximation and learning by greedy algorithms

DOI10.1214/009053607000000631zbMath1138.62019arXiv0803.1718OpenAlexW2037842665MaRDI QIDQ2477053

Wolfgang Dahmen, Ronald A. DeVore, Albert Cohen, Andrew R. Barron

Publication date: 12 March 2008

Published in: The Annals of Statistics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/0803.1718

zbMATH Keywords

neural networks interpolation spaces statistical learning convergence rates for greedy algorithms

Mathematics Subject Classification ID

Nonparametric regression and quantile regression (62G08) Learning and adaptive systems in artificial intelligence (68T05) Multidimensional problems (41A63) Applications of functional analysis in probability theory and statistics (46N30) Approximation by arbitrary nonlinear expressions; widths and entropy (41A46)

Related Items

Greedy algorithms for prediction, Optimality of the rescaled pure greedy learning algorithms, Stochastic subspace correction in Hilbert space, LOL selection in high dimension, Turnpike in optimal control of PDEs, ResNets, and beyond, Linear and nonlinear approximation of spherical radial basis function networks, High-dimensional variable selection, On some similarities and differences between deep neural networks and kernel learning machines, Two-Layer Neural Networks with Values in a Banach Space, Results and questions on a nonlinear approximation approach for solving high-dimensional partial differential equations, Asymptotics for high-dimensional covariance matrices and quadratic forms with applications to the trace functional and shrinkage, Toward Efficient Ensemble Learning with Structure Constraints: Convergent Algorithms and Applications, Rescaled pure greedy algorithm for Hilbert and Banach spaces, A NONPARAMETRIC ESTIMATOR FOR THE COVARIANCE FUNCTION OF FUNCTIONAL DATA, Uniform approximation rates and metric entropy of shallow neural networks, Proper generalized decompositions and separated representations for the numerical solution of high dimensional stochastic problems, Nearly optimal minimax estimator for high-dimensional sparse linear regression, Wavelet neural networks functional approximation and application, Unified error estimate for weak biorthogonal Greedy algorithms, Training Neural Networks as Learning Data-adaptive Kernels: Provable Representation and Approximation Benefits, Fully corrective gradient boosting with squared hinge: fast learning rates and early stopping, On the selection of predictors by using greedy algorithms and information theoretic criteria, Characterization of the variation spaces corresponding to shallow neural networks, Adaptive piecewise Poly-Sinc methods for function approximation, On the convergence rate of kernel-based sequential greedy regression, ReLU neural network Galerkin BEM, Aggregation of estimators and stochastic optimization, Growing axons: greedy learning of neural networks with application to function approximation, Micro-macro models for viscoelastic fluids: modelling, mathematics and numerics, Quadratic Neural Networks for Solving Inverse Problems, Lasso, iterative feature selection and the correlation selector: oracle inequalities and numerical performances, The Lasso as an \(\ell _{1}\)-ball model selection procedure, Greedy training algorithms for neural networks and applications to PDEs, Structured, sparse regression with application to HIV drug resistance, Greedy and randomized versions of the multiplicative Schwarz method, Convergence rate of the semi-supervised greedy algorithm, A multiscale virtual element method for elliptic problems in heterogeneous porous media, On the Convergence of a Greedy Algorithm for the Solution of the Problem for the Construction of Monotone Regression, On \(n\)-term approximation with positive coefficients, Wavelets centered on a knot sequence: theory, construction, and applications, Provable approximation properties for deep neural networks, ESTIMATION FOR THE PREDICTION OF POINT PROCESSES WITH MANY COVARIATES, A Sequential Significance Test for Treatment by Covariate Interactions, Restricted strong convexity implies weak submodularity, Almost optimal estimates for approximation and learning by radial basis function networks, Schwarz iterative methods: infinite space splittings, Learning Rates of l^q Coefficient Regularization Learning with Gaussian Kernel, Density estimation with quadratic loss: a confidence intervals method, On the sparseness of 1-norm support vector machines, Greedy Algorithms for Optimal Measurements Selection in State Estimation Using Reduced Models, How To Best Sample a Solution Manifold?, Iterative feature selection in least square regression estimation, Semi-nonparametric approximation and index options, Penalized empirical relaxed greedy algorithm for fixed design Gaussian regression, Covariate selection for accelerated failure time data, Elastic-net regularization in learning theory, Semiparametric estimation of plane similarities: application to fast computation of aeronautic loads, A unified way of analyzing some greedy algorithms, Duality gap estimates for weak Chebyshev greedy algorithms in Banach spaces, Unnamed Item, Sure Independence Screening for Ultrahigh Dimensional Feature Space, Efficiency of the weak Rescaled Pure Greedy Algorithm, On universal estimators in learning theory, Sampling based approximation of linear functionals in reproducing kernel Hilbert spaces, Duality gap estimates for a class of greedy optimization algorithms in Banach spaces, A New Function Space from Barron Class and Application to Neural Network Approximation

Cites Work