Understanding neural networks with reproducing kernel Banach spaces

DOI10.1016/j.acha.2022.08.006OpenAlexW3199436419MaRDI QIDQ2105111

Stefano Vigogna, Ernesto De Vito, Lorenzo Rosasco, Francesca Bartolucci

Publication date: 8 December 2022

Published in: Applied and Computational Harmonic Analysis (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2109.09710

zbMATH Keywords

neural networksRadon transformreproducing kernel Banach spacesrepresenter theorem

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Hilbert spaces with reproducing kernels (= (proper) functional Hilbert spaces, including de Branges-Rovnyak and other structured spaces) (46E22)

Related Items

Explicit representations for Banach subspaces of Lizorkin distributions ⋮ Sparse machine learning in Banach spaces ⋮ The Mori-Zwanzig formulation of deep learning

Uses Software

• PDCO

Cites Work

• 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
• On the range of the Radon transform and its dual
• Theory of function spaces
• Functional analysis, Sobolev spaces and partial differential equations
• Spline solutions to L\(^1\) extremal problems in one and several variables
• The Radon transform.
• Approximation and estimation bounds for artificial neural networks
• Reproducing kernel Banach spaces with the \(\ell^1\) norm
• A distribution-free theory of nonparametric regression
• Sparsity of solutions for variational inverse problems with finite-dimensional data
• The Radon transform on Euclidean spaces, compact two-point homogeneous spaces and Grassmann manifolds
• Some results on Tchebycheffian spline functions and stochastic processes
• Atomic Decomposition by Basis Pursuit
• The Mathematics of Computerized Tomography
• On the mathematical foundations of learning
• Reproducing Kernel Banach Spaces with the ℓ¹ Norm II: Error Analysis for Regularized Least Square Regression
• VECTOR VALUED REPRODUCING KERNEL HILBERT SPACES AND UNIVERSALITY
• Support Vector Machines
• Universal approximation bounds for superpositions of a sigmoidal function
• Splines Are Universal Solutions of Linear Inverse Problems with Generalized TV Regularization
• Regularized learning schemes in feature Banach spaces
• Multikernel Regression with Sparsity Constraint
• Reconciling modern machine-learning practice and the classical bias–variance trade-off
• On Representer Theorems and Convex Regularization
• Uniform asymptotic expansions at a caustic
• Breaking the Curse of Dimensionality with Convex Neural Networks
• Generalized Mercer Kernels and Reproducing Kernel Banach Spaces
• The Ridgelet transform of distributions
• ℓ1 Regularization in Infinite Dimensional Feature Spaces
• A Correspondence Between Bayesian Estimation on Stochastic Processes and Smoothing by Splines
• Theory of Reproducing Kernels
• Approximation by superpositions of a sigmoidal function