Kolmogorov width decay and poor approximators in machine learning: shallow neural networks, random feature models and neural tangent kernels
approximation theoryBarron spacecurse of dimensionalityKolmogorov widthmulti-layer networkneural tangent kernelpopulation riskrandom feature modelreproducing kernel Hilbert spacetwo-layer network
Approximation by other special function classes (41A30) Abstract approximation theory (approximation in normed linear spaces and other abstract spaces) (41A65) Banach spaces of continuous, differentiable or analytic functions (46E15) Hilbert spaces with reproducing kernels (= (proper) functional Hilbert spaces, including de Branges-Rovnyak and other structured spaces) (46E22) Artificial neural networks and deep learning (68T07)
- Tractability of approximation by general shallow networks
- Limitations of shallow nets approximation
- Approximation of functions from Korobov spaces by shallow neural networks
- Linearized two-layers neural networks in high dimension
- Error bounds for deep ReLU networks using the Kolmogorov-Arnold superposition theorem
- A comparative analysis of optimization and generalization properties of two-layer neural network and random feature models under gradient descent dynamics
- A priori estimates of the population risk for two-layer neural networks
- Applied functional analysis. Functional analysis, Sobolev spaces and elliptic differential equations
- Approximation by superpositions of a sigmoidal function
- Breaking the curse of dimensionality with convex neural networks
- Functional analysis, Sobolev spaces and partial differential equations
- scientific article; zbMATH DE number 3246460 (Why is no real title available?)
- On the rate of convergence in Wasserstein distance of the empirical measure
- Optimal Transport
- Understanding machine learning. From theory to algorithms
- Universal approximation bounds for superpositions of a sigmoidal function
- Generalization error of GAN from the discriminator's perspective
- Representation formulas and pointwise properties for Barron functions
- Neural network regression for Bermudan option pricing
- Kolmogorov n-width and Lagrangian physics-informed neural networks: a causality-conforming manifold for convection-dominated PDEs
- When do neural networks outperform kernel methods?*
- Nonlinear weighted directed acyclic graph and a priori estimates for neural networks
- Deep ReLU neural networks overcome the curse of dimensionality for partial integrodifferential equations
- A class of dimension-free metrics for the convergence of empirical measures
- A priori generalization error analysis of two-layer neural networks for solving high dimensional Schrödinger eigenvalue problems
- Harmonic analysis of network systems via kernels and their boundary realizations
- Kolmogorov Width Decay and Poor Approximators in Machine Learning: Shallow Neural Networks, Random Feature Models and Neural Tangent Kernels
- Embeddings between Barron spaces with higher-order activation functions
- On the physical interpretation of neural PDEs
- An L^2 analysis of reinforcement learning in high dimensions with kernel and neural network approximation
- Reinforcement learning with function approximation: from linear to nonlinear
- Duality for neural networks through reproducing kernel Banach spaces
- Curse of dimensionality in neural network optimization
This page was built for publication: Kolmogorov width decay and poor approximators in machine learning: shallow neural networks, random feature models and neural tangent kernels
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2226529)
