Dependence of Computational Models on Input Dimension: Tractability of Approximation and Optimization Tasks

DOI10.1109/TIT.2011.2169531zbMath1365.68373OpenAlexW2074381721MaRDI QIDQ5272131

Paul C. Kainen, Vera Kurková, Marcello Sanguineti

Publication date: 12 July 2017

Published in: IEEE Transactions on Information Theory (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1109/tit.2011.2169531

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Approximation methods and heuristics in mathematical programming (90C59)

Related Items (16)

On the curse of dimensionality in the Ritz method ⋮ Probabilistic lower bounds for approximation by shallow perceptron networks ⋮ Wavelet neural networks functional approximation and application ⋮ Universal approximation with quadratic deep networks ⋮ Robust min-max optimal control design for systems with uncertain models: a neural dynamic programming approach ⋮ Two fast and accurate heuristic RBF learning rules for data classification ⋮ Smart sampling and incremental function learning for very large high dimensional data ⋮ On the approximation of functions by tanh neural networks ⋮ Approximation capabilities of neural networks on unbounded domains ⋮ Lower bounds for artificial neural network approximations: a proof that shallow neural networks fail to overcome the curse of dimensionality ⋮ Accuracy of approximations of solutions to Fredholm equations by kernel methods ⋮ Approximate dynamic programming for stochastic \(N\)-stage optimization with application to optimal consumption under uncertainty ⋮ Negative results for approximation using single layer and multilayer feedforward neural networks ⋮ Almost optimal estimates for approximation and learning by radial basis function networks ⋮ Complexity of Shallow Networks Representing Finite Mappings ⋮ Correlations of random classifiers on large data sets

This page was built for publication: Dependence of Computational Models on Input Dimension: Tractability of Approximation and Optimization Tasks