Geometric Upper Bounds on Rates of Variable-Basis Approximation
From MaRDI portal
Publication:3604968
DOI10.1109/TIT.2008.2006383zbMath1319.68177OpenAlexW2099706683MaRDI QIDQ3604968
Vera Kurková, Marcello Sanguineti
Publication date: 24 February 2009
Published in: IEEE Transactions on Information Theory (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1109/tit.2008.2006383
neural networksrates of approximationmodel complexityvariable-basis approximationApproximation from a dictionary
Learning and adaptive systems in artificial intelligence (68T05) Signal theory (characterization, reconstruction, filtering, etc.) (94A12)
Related Items
Suboptimal solutions to dynamic optimization problems via approximations of the policy functions ⋮ Minimizing sequences for a family of functional optimal estimation problems ⋮ On the approximation of functions by tanh neural networks ⋮ Approximation capabilities of neural networks on unbounded domains ⋮ Convergence rates for shallow neural networks learned by gradient descent ⋮ Complexity estimates based on integral transforms induced by computational units ⋮ 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 ⋮ Dynamic programming and value-function approximation in sequential decision problems: error analysis and numerical results ⋮ Can dictionary-based computational models outperform the best linear ones? ⋮ Approximate dynamic programming for stochastic \(N\)-stage optimization with application to optimal consumption under uncertainty ⋮ New insights into Witsenhausen's counterexample ⋮ Estimates of variation with respect to a set and applications to optimization problems ⋮ Some comparisons of complexity in dictionary-based and linear computational models ⋮ Optimization based on quasi-Monte Carlo sampling to design state estimators for non-linear systems ⋮ Estimates of the approximation error using Rademacher complexity: Learning vector-valued functions ⋮ Value and Policy Function Approximations in Infinite-Horizon Optimization Problems ⋮ Suboptimal Policies for Stochastic $$N$$-Stage Optimization: Accuracy Analysis and a Case Study from Optimal Consumption ⋮ High-order approximation rates for shallow neural networks with cosine and \(\mathrm{ReLU}^k\) activation functions
