Banach space representer theorems for neural networks and ridge splines
From MaRDI portal
Publication:4998934
Spline approximation (41A15) Hilbert spaces with reproducing kernels (= (proper) functional Hilbert spaces, including de Branges-Rovnyak and other structured spaces) (46E22) Applications of functional analysis in optimization, convex analysis, mathematical programming, economics (46N10) Learning and adaptive systems in artificial intelligence (68T05)
Recommendations
- When is there a representer theorem? Nondifferentiable regularisers and Banach spaces
- Understanding neural networks with reproducing kernel Banach spaces
- A unifying representer theorem for inverse problems and machine learning
- A representer theorem for deep neural networks
- When is there a representer theorem? Reflexive Banach spaces
Cites work
- 10.1162/153244303321897690
- A representer theorem for deep neural networks
- Approximation by superpositions of a sigmoidal function
- Best approximation by ridge functions in L_p-spaces
- Breaking the coherence barrier: a new theory for compressed sensing
- Breaking the curse of dimensionality with convex neural networks
- Denseness of the spaces $Φ_V$ of Lizorkin type in the mixed $L^{p̅}(ℝ^n)$-spaces
- Generalized Mercer kernels and reproducing kernel Banach spaces
- Generalized sampling and infinite-dimensional compressed sensing
- Harmonic analysis of neural networks
- scientific article; zbMATH DE number 1804115 (Why is no real title available?)
- scientific article; zbMATH DE number 3890068 (Why is no real title available?)
- scientific article; zbMATH DE number 45848 (Why is no real title available?)
- scientific article; zbMATH DE number 3533448 (Why is no real title available?)
- scientific article; zbMATH DE number 3537179 (Why is no real title available?)
- scientific article; zbMATH DE number 1324223 (Why is no real title available?)
- scientific article; zbMATH DE number 741219 (Why is no real title available?)
- scientific article; zbMATH DE number 1889798 (Why is no real title available?)
- scientific article; zbMATH DE number 3240665 (Why is no real title available?)
- scientific article; zbMATH DE number 3295108 (Why is no real title available?)
- Integral geometry and Radon transforms
- Intermediate spaces and interpolation, the complex method
- Introduction to applied partial differential equations
- Inverse problems in spaces of measures
- ℓ1 Regularization in Infinite Dimensional Feature Spaces
- Locally adaptive regression splines
- Morrey and Campanato meet Besov, Lizorkin and Triebel
- Multilayer feedforward networks are universal approximators
- Neural network with unbounded activation functions is universal approximator
- On representer theorems and convex regularization
- Optimal reconstruction of a function from its projections
- Provable approximation properties for deep neural networks
- Reproducing kernel Banach spaces for machine learning
- Ridge functions
- Scattered Data Approximation
- Some problems in the theory of ridge functions
- Some results on Tchebycheffian spline functions and stochastic processes
- Sparsity of solutions for variational inverse problems with finite-dimensional data
- Spline solutions to L\(^1\) extremal problems in one and several variables
- Splines are universal solutions of linear inverse problems with generalized TV regularization
- The Calderón reproducing formula, windowed \(X\)-ray transforms, and Radon transforms in \(L^p\)-spaces
- The ridgelet transform of distributions
- Tikhonov, Ivanov and Morozov regularization for support vector machine learning
- Understanding machine learning. From theory to algorithms
- Universal approximation bounds for superpositions of a sigmoidal function
Cited in
(54)- Sparsest piecewise-linear regression of one-dimensional data
- Understanding neural networks with reproducing kernel Banach spaces
- Representation formulas and pointwise properties for Barron functions
- Uniform approximation rates and metric entropy of shallow neural networks
- Nonconvex regularization for sparse neural networks
- Richards's curve induced Banach space valued multivariate neural network approximation
- Greedy training algorithms for neural networks and applications to PDEs
- The Random Feature Model for Input-Output Maps between Banach Spaces
- scientific article; zbMATH DE number 7626727 (Why is no real title available?)
- scientific article; zbMATH DE number 7626740 (Why is no real title available?)
- Two-Layer Neural Networks with Values in a Banach Space
- What Kinds of Functions Do Deep Neural Networks Learn? Insights from Variational Spline Theory
- A representer theorem for deep neural networks
- Spline representation and redundancies of one-dimensional ReLU neural network models
- A Regularity Theory for Static Schrödinger Equations on \(\boldsymbol{\mathbb{R}}\)d in Spectral Barron Spaces
- Neural network approximation
- Training Neural Networks as Learning Data-adaptive Kernels: Provable Representation and Approximation Benefits
- Explicit representations for Banach subspaces of Lizorkin distributions
- Characterization of the variation spaces corresponding to shallow neural networks
- Sparse machine learning in Banach spaces
- Optimal learning
- A duality approach to regularized learning problems in Banach spaces
- The Mori-Zwanzig formulation of deep learning
- Neural network approximation and estimation of classifiers with classification boundary in a Barron class
- Measuring Complexity of Learning Schemes Using Hessian-Schatten Total Variation
- Integral representations of shallow neural network with Rectified Power Unit activation function
- Distributional extension and invertibility of the k-plane transform and its dual
- A unified Fourier slice method to derive ridgelet transform for a variety of depth-2 neural networks
- MARS via lasso
- Weighted variation spaces and approximation by shallow ReLU networks
- Embeddings between Barron spaces with higher-order activation functions
- From kernel methods to neural networks: a unifying variational formulation
- Compositional function spaces for deep learning
- Representation of the solution of fractional Schrödinger equations with shallow neural network
- Conditional gradients for total variation regularization with PDE constraints: a graph cuts approach
- Enhanced feature learning via regularisation: integrating neural networks and kernel methods
- On extremal points for some vectorial total variation seminorms
- Optimal approximation of zonoids and uniform approximation by shallow neural networks
- ReLU neural networks with linear layers are biased towards single- and multi-index models
- Integral probability metrics meet neural networks: the Radon-Kolmogorov-Smirnov test
- Learning a sparse representation of Barron functions with the inverse scale space flow
- Embedding inequalities for Barron-type spaces
- Duality for neural networks through reproducing kernel Banach spaces
- Random ReLU neural networks as non-Gaussian processes
- Convergence analysis of the discretization of continuous-domain inverse problems
- Efficient estimation of single-index models with deep ReQU neural networks
- Function-space optimality of neural architectures with multivariate nonlinearities
- Sampling theory for super-resolution with implicit neural representations
- A Lipschitz spaces view of infinitely wide shallow neural networks
- Elliptic Regularity Theory in Barron Spaces and Applications to the Deep Ritz Method
- A general theory for exact sparse representation recovery in convex optimization
- Adaptive vector-valued splines for the resolution of inverse problems
- Deep P-Spline: Theory, Fast Tuning, and Application
- Interpolation and inverse problems in spectral barron spaces
This page was built for publication: Banach space representer theorems for neural networks and ridge splines
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4998934)
