Fundamentality of ridge functions
For \(d,n\in \mathbb{N}\) denote by \(\Omega\) the set of all real \(d\times n\) matrices and let \(M(\Omega)= \text{span} (g(A.x)\): \(A\in\Omega\), \(g\in C(\mathbb{R}^ d, \mathbb{R})\}\), where \(C(\mathbb{R}^ d, \mathbb{R})\) denotes the space of all continuous functions \(g: \mathbb{R}^ d\to \mathbb{R}\) For \(d=1\) the functions in \(M(\Omega)\) are called ridge functions and they are relevant in problems of tomography, neural networks, approximation theory etc. The main question treated in this paper is the density of \(M(\Omega)\) in \(C(\mathbb{R}^ n, \mathbb{R})\), with respect to the topology of uniform convergence of compacta. For \(A\in\Omega\) let \(L(A)\) be the span of the \(d\) rows of \(A\) and let \(L(\Omega)= \bigcup\{ L(A)\): \(A\in\Omega\}\). Let \(H_ n^ k\) denote the set of homogeneous polynomials \(p\) of \(n\) variables \[ -p(s)= \sum_{| m|=k} c_ m s^ m, \qquad m=(m_ 1,\dots, m_ n)\in \mathbb{Z}^ n, \] \(| m|= m_ 1+\dots +m_ n\), \(s^ m= s_ 1^{m_ 1}\dots s_ n^{m_ n}\), and let \(H^ n= \bigcup_{n=0^ \infty} H_ k^ n\). Then \(M(\Omega)\) is dense in \(C(\mathbb{R}^ n, \mathbb{R})\) iff the only polynomial in \(H^ n\) vanishing identically on \(L(\Omega)\) is the zero polynomial (Theorem 2.1). This is equivalent to the assertion that \(M(\Omega)\) explicitly contains the polynomials. If \(k\in \mathbb{N}\) is fixed, then \[ M_ k(\Omega)= \Biggl\{ \sum_{i=1}^ k a_ i g(A_ i x):\;a_ i\in \mathbb{R},\;A_ i\in \Omega,\;i=1,\dots, k,\;g\in C(\mathbb{R}^ d, \mathbb{R}) \Biggr\} \] is not dense in \(C(\mathbb{R}^ d, \mathbb{R})\) (Theorem 5.1). Theorems 2.1 and 4.1 in this paper are obtained (in the case \(d=1\)) by \textit{B. A. Vostrecov} and \textit{M. A. Krejnes}, Dokl. Akad. Nauk SSSR 140, 1237-1240 (1961; Zbl 0106.273) and ibid. 144, 1212-1214 (1962; Zbl 0196.439).
- scientific article; zbMATH DE number 4052203
- Ridge functions
- On approximation by ridge functions
- On some properties of smooth sums of ridge functions
- Smoothness and uniqueness in ridge function representation
- The fundamentality of sets of ridge functions
- Ridge functions and applications in neural networks
- Characterization of an extremal sum of ridge functions
- On the proximinality of ridge functions
- On some aspects of approximation of ridge functions
- The fundamentality of sets of ridge functions
- Constructive methods of approximation by ridge functions and radial functions
- Identifying linear combinations of ridge functions
- On best approximation by ridge functions
- On the approximation of functional classes equipped with a uniform measure using ridge functions
- Approximation by spherical waves in L^p-spaces
- Some problems in the theory of ridge functions
- A note on continuous sums of ridge functions
- On best approximation of classes by radial functions
- Approximation by ridge function fields over compact sets
- TDI-subspaces of \(C(\mathbb{R}^ d)\) and some density problems from neural networks
- On the approximation by single hidden layer feedforward neural networks with fixed weights
- Multivariate complex B-splines and Dirichlet averages
- Decoupling multivariate polynomials: interconnections between tensorizations
- On some aspects of approximation of ridge functions
- Range descriptions for the spherical mean Radon transform
- Characterization of an extremal sum of ridge functions
- Harmonic analysis and integral transforms associated with a class of a system of partial differential operators
- On the representation by linear superpositions
- On the error of approximation by ridge functions with two fixed directions
- Range description for a spherical mean transform on spaces of constant curvature
- Mathematics of Hybrid Imaging: A Brief Review
- Mathematics of thermoacoustic tomography
- scientific article; zbMATH DE number 4052203 (Why is no real title available?)
- Deep distributed convolutional neural networks: universality
- Image reconstruction from radially incomplete spherical Radon data
- On the approximation by neural networks with bounded number of neurons in hidden layers
- Semiglobal optimal feedback stabilization of autonomous systems via deep neural network approximation
- Mean Dimension of Ridge Functions
- Approximation properties of ridge functions and extreme learning machines
- Ridge functions
- Consistency of Ridge Function Fields for Varying Nonparametric Regression
- Approximation by sums of ridge functions with fixed directions
- scientific article; zbMATH DE number 6257179 (Why is no real title available?)
- Approximating functions with multi-features by deep convolutional neural networks
- Theory of deep convolutional neural networks. III: Approximating radial functions
- Deep learning theory of distribution regression with CNNs
- Approximation of curve-based sleeve functions in high dimensions
- The ridge function representation of polynomials and an application to neural networks
- Approximating functions with additive ridge features by deep \(\mathrm{ReLU}^k\) convolutional neural networks
- Learning theory of distribution regression with neural networks
- Finding optimal weight vectors for ridge function approximation in L^2(D)
- Smoothness and uniqueness in ridge function representation
- A representation problem for smooth sums of ridge functions
- Geometric properties of the ridge function manifold
- Representation of multivariate functions by sums of ridge functions
- On a smoothness problem in ridge function representation
This page was built for publication: Fundamentality of ridge functions
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1318241)
