From kernel methods to neural networks: a unifying variational formulation

Artificial neural networks and deep learning (68T07) Radon transform (44A12) Applications of functional analysis in optimization, convex analysis, mathematical programming, economics (46N10) Linear operators and ill-posed problems, regularization (47A52)

Cites Work

Title not available (Why is that?)
Title not available (Why is that?)
Title not available (Why is that?)
Title not available (Why is that?)
Title not available (Why is that?)
Title not available (Why is that?)
Title not available (Why is that?)
Title not available (Why is that?)
Title not available (Why is that?)
Title not available (Why is that?)
Title not available (Why is that?)
Title not available (Why is that?)
Title not available (Why is that?)
Title not available (Why is that?)
Title not available (Why is that?)
Title not available (Why is that?)
Interpolation of scattered data: distance matrices and conditionally positive definite functions
Kernel methods in machine learning
Multivariate interpolation at arbitrary points made simple
Denseness of the Lizorkin-type spaces \(Phi_ v \)in \(L_ p(\)\(R^ n)\)
Approximation by superposition of sigmoidal and radial basis functions
Spline solutions to L\(^1\) extremal problems in one and several variables
On 'best' interpolation
Locally adaptive regression splines
Multilayer feedforward networks are universal approximators
Understanding neural networks with reproducing kernel Banach spaces
A unifying representer theorem for inverse problems and machine learning
Sparsity of solutions for variational inverse problems with finite-dimensional data
Neural network with unbounded activation functions is universal approximator
Convex optimization in sums of Banach spaces
Kernels for Vector-Valued Functions: A Review
Integral Geometry and Radon Transforms
Regularization Algorithms for Learning That Are Equivalent to Multilayer Networks
An Introduction to Sparse Stochastic Processes
Classical Fourier Analysis
Universal approximation bounds for superpositions of a sigmoidal function
Radial Basis Functions
Splines Are Universal Solutions of Linear Inverse Problems with Generalized TV Regularization
On Different Facets of Regularization Theory
Fractional Splines and Wavelets
Multikernel Regression with Sparsity Constraint
What Kinds of Functions Do Deep Neural Networks Learn? Insights from Variational Spline Theory
On Representer Theorems and Convex Regularization
Uniform asymptotic expansions at a caustic
Breaking the Curse of Dimensionality with Convex Neural Networks
The Ridgelet transform of distributions
Theory of Reproducing Kernels
Scattered Data Approximation
Approximation by superpositions of a sigmoidal function
Explicit representations for Banach subspaces of Lizorkin distributions

This page was built for publication: From kernel methods to neural networks: a unifying variational formulation

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6659493)