On the representation by linear superpositions

DOI10.1016/J.JAT.2007.09.003zbMATH Open1136.41001arXiv1501.05268OpenAlexW1986593967MaRDI QIDQ2425409FDOQ2425409

Vugar E. Ismailov

Publication date: 5 May 2008

Published in: Journal of Approximation Theory (Search for Journal in Brave)

Abstract: In a number of papers, Y. Sternfeld investigated the problems of representation of continuous and bounded functions by linear superpositions. In particular, he proved that if such representation holds for continuous functions, then it holds for bounded functions. We consider the same problem without involving any topology and establish a rather practical necessary and sufficient condition for representability of an arbitrary function by linear superpositions. In particular, we show that if some representation by linear superpositions holds for continuous functions, then it holds for all functions. This will lead us to the analogue of the well-known Kolmogorov superposition theorem for multivariate functions on the $d$-dimensional unit cube.

Full work available at URL: https://arxiv.org/abs/1501.05268

Recommendations

• A note on the representation of continuous functions by linear superpositions
• scientific article; zbMATH DE number 964891
• Computational aspects of Kolmogorov's superposition theorem
• Superposition stetiger Abbildungen
• Approximation of continuous functions of several variables by an arbitrary nonlinear continuous function of one variable, linear functions, and their superpositions

zbMATH Keywords

ridge functionlinear superpositionclosed path

Mathematics Subject Classification ID

Multidimensional problems (41A63) Interpolation in approximation theory (41A05) Representation and superposition of functions (26B40)

Cites Work

• Projection pursuit
• Fundamentality of ridge functions
• Title not available (Why is that?)
• Constructive methods of approximation by ridge functions and radial functions
• Title not available (Why is that?)
• On best approximation by ridge functions
• Title not available (Why is that?)
• Approximation by Ridge functions and neural networks with one hidden layer
• Identifying linear combinations of ridge functions
• Ridgelets: estimating with ridge functions
• Title not available (Why is that?)
• Optimal reconstruction of a function from its projections
• Interpolation by Ridge functions
• Title not available (Why is that?)
• On Nonlinear Functions of Linear Combinations
• Dimension of metric spaces and Hilbert’s problem 13
• Title not available (Why is that?)
• Approximation by Ridge Functions and Neural Networks
• On approximation by ridge functions
• Dimension, superposition of functions and separation of points, in compact metric spaces
• Uniformly separating families of functions
• An improvement in the superposition theorem of Kolmogorov
• Metric Entropy, Widths, and Superpositions of Functions
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• 0n the best approximation by ridge functions in the uniform norm
• On the approximation of functional classes equipped with a uniform measure using ridge functions
• When is \(f(x_1,x_1,\dots,x_n)= u_1(x_1)+ u_2(x_2)+\cdots+ u_n(x_n)\)?
• Uniform separation of points and measures and representation by sums of algebras
• When is \(f(x,y)=u(x)+v(y)\)?
• A Superposition Theorem for Bounded Continuous Functions
• Title not available (Why is that?)
• A Representation Theorem for Continuous Functions of Several Variables
• Tomographic reconstruction from arbitrary directions using ridge functions

Cited In (20)

• On the uniqueness of representation by linear superpositions
• Peculiarities of bounds on states through the concept of linear superposition
• A note on the equioscillation theorem for best ridge function approximation
• Title not available (Why is that?)
• Approximation by ridge functions and neural networks with a bounded number of neurons
• On the error of approximation by ridge functions with two fixed directions
• On interpolation properties of exterior functions in Kolmogorov superpositions
• On the approximation by neural networks with bounded number of neurons in hidden layers
• Some problems in the theory of ridge functions
• A note on the representation of continuous functions by linear superpositions
• Approximation by sums of ridge functions with fixed directions
• Interpolation on lines by ridge functions
• Approximation by neural networks with weights varying on a finite set of directions
• The ridge function representation of polynomials and an application to neural networks
• Computing the Approximation Error for Neural Networks with Weights Varying on Fixed Directions
• Title not available (Why is that?)
• On the representation by sums of algebras of continuous functions
• Der Kolmogoroff'sche Darstellungsatz bei halbstetigen Funktionen
• A three layer neural network can represent any multivariate function
• Superposition stetiger Abbildungen

This page was built for publication: On the representation by linear superpositions

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2425409)