On the approximation of functional classes equipped with a uniform measure using ridge functions
From MaRDI portal
Publication:1300147
DOI10.1006/jath.1998.3305zbMath0940.41009MaRDI QIDQ1300147
Joel Ratsaby, Ron Meir, Vitaly Maiorov
Publication date: 10 May 2000
Published in: Journal of Approximation Theory (Search for Journal in Brave)
Full work available at URL: https://semanticscholar.org/paper/86443ba0c1addebf18966e54fbf0cace5ecc9f9c
nonlinear approximation; uniform measure; probabilistic width; approximation by ridge functions; approximation of Besov-type class
41A63: Multidimensional problems
41A30: Approximation by other special function classes
41A46: Approximation by arbitrary nonlinear expressions; widths and entropy
Related Items
The Kolmogorov-Arnold representation theorem revisited, The ridge function representation of polynomials and an application to neural networks, Some problems in the theory of ridge functions, On best approximation of classes by radial functions, Limitations of shallow nets approximation, Characterization of an extremal sum of ridge functions, Approximation of Sobolev classes by polynomials and ridge functions, On the representation by linear superpositions, On the error of approximation by ridge functions with two fixed directions, Phase transitions in rate distortion theory and deep learning
Cites Work
- Networks and the best approximation property
- On best approximation by ridge functions
- Approximation and estimation bounds for artificial neural networks
- Fundamentality of ridge functions
- Linear widths of function spaces equipped with the Gaussian measure
- Harmonics on homogeneous manifolds
- Probabilistic and average linear width in \(L_ \infty\)-norm with respect to \(r\)-fold Wiener measure
- On the near optimality of the stochastic approximation of smooth functions by neural networks
- Approximation by Ridge Functions and Neural Networks
- Probability Inequalities for Sums of Bounded Random Variables
- Lower Bounds for Approximation by Nonlinear Manifolds
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item