Identifying linear combinations of ridge functions
From MaRDI portal
This paper is about an inverse problem. Let a given function \(f(\mathbf x)\) be some sum of ridge functions of the form \(\sum_{i=1}^mg_i(\mathbf a^i\cdot\mathbf x)\). We just know an upper bound on \(m\). We seek to identify the functions \(g_i\) and also to identify the directions \(\mathbf a^i\) from such limited information. Several ways to solve this nonlinear problem are discussed in this work.
Recommendations
- Linear/ridge expansions: enhancing linear approximations by ridge functions
- Ridge functions
- Publication:4938096
- scientific article; zbMATH DE number 6257179
- Ridgelets: estimating with ridge functions
- scientific article; zbMATH DE number 3967720
- Representation of multivariate functions by sums of ridge functions
- Ridge functions and orthonormal ridgelets
- Interpolation on lines by ridge functions
Cites work
- Fundamentality of ridge functions
- Generalised functions and their convolution
- scientific article; zbMATH DE number 3114615 (Why is no real title available?)
- scientific article; zbMATH DE number 1083108 (Why is no real title available?)
- scientific article; zbMATH DE number 3001304 (Why is no real title available?)
- scientific article; zbMATH DE number 1404611 (Why is no real title available?)
- scientific article; zbMATH DE number 3225653 (Why is no real title available?)
- On Nonlinear Functions of Linear Combinations
- Optimal reconstruction of a function from its projections
- Projection-based approximation and a duality with kernel methods
- Reconstructing a neural net from its output
Cited in
(23)- 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
- The recovery of ridge functions on the hypercube suffers from the curse of dimensionality
- On the representation by bivariate ridge functions
- Stable recovery of entangled weights: towards robust identification of deep neural networks from minimal samples
- Recovery of regular ridge functions on the ball
- Linear/ridge expansions: enhancing linear approximations by ridge functions
- On some aspects of approximation of ridge functions
- Characterization of an extremal sum of ridge functions
- On the representation by linear superpositions
- Robust recovery of stream of pulses using convex optimization
- On some properties of smooth sums of ridge functions
- Approximation by sums of ridge functions with fixed directions
- The ridge function representation of polynomials and an application to neural networks
- On the representability of a continuous multivariate function by sums of ridge functions
- On the representability of a smooth function by sums of generalized ridge functions
- Efficient identification of wide shallow neural networks with biases
- Smoothness and uniqueness in ridge function representation
- Entropy and sampling numbers of classes of ridge functions
- A representation problem for smooth sums of ridge functions
- On a smoothness problem in ridge function representation
This page was built for publication: Identifying linear combinations of ridge functions
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1277211)
