Approximation and learning of convex superpositions

DOI10.1006/jcss.1997.1506zbMath0880.68105OpenAlexW1994108380MaRDI QIDQ1370865

Pascal Koiran, Leonid Gurvits

Publication date: 19 January 1998

Published in: Journal of Computer and System Sciences (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1006/jcss.1997.1506

zbMATH Keywords

neural networks

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Related Items (10)

Estimates of covering numbers of convex sets with slowly decaying orthogonal subsets ⋮ A Sobolev-type upper bound for rates of approximation by linear combinations of Heaviside plane waves ⋮ Best approximation by linear combinations of characteristic functions of half-spaces. ⋮ 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 ⋮ An Integral Upper Bound for Neural Network Approximation ⋮ Approximative compactness of linear combinations of characteristic functions ⋮ Rates of minimization of error functionals over Boolean variable-basis functions ⋮ Depth separations in neural networks: what is actually being separated?

Cites Work

• Unnamed Item
• Unnamed Item
• U-processes: Rates of convergence
• Universal Donsker classes and metric entropy
• Characterization of the law of the iterated logarithm in Banach spaces
• Estimation of dependences based on empirical data. Transl. from the Russian by Samuel Kotz
• Decision theoretic generalizations of the PAC model for neural net and other learning applications
• Central limit theorems for empirical measures
• Discrepancy and approximations for bounded VC-dimension
• Efficient distribution-free learning of probabilistic concepts
• Fat-shattering and the learnability of real-valued functions
• Learnability and the Vapnik-Chervonenkis dimension
• Vapnik-Chervonenkis Classes of Definable Sets
• Universal approximation bounds for superpositions of a sigmoidal function
• Scale-sensitive dimensions, uniform convergence, and learnability
• Real Analysis and Probability
• Convergence of stochastic processes

This page was built for publication: Approximation and learning of convex superpositions