Gaussian random field approximation via Stein's method with applications to wide random neural networks

DOI10.1016/J.ACHA.2024.101668MaRDI QIDQ6567398zbMATHFDO

Authors Krishnakumar Balasubramanian, Larry Goldstein, Nathan Ross, Adil Salim

Publication date 5 July 2024

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

zbMATH Keywords

Gaussian random fieldStein's methoddistributional approximationdeep neural networksLaplacian-based smoothing

Mathematics Subject Classification ID

Random fields (60G60) Artificial neural networks and deep learning (68T07) Central limit and other weak theorems (60F05)

Recommendations

• Random neural networks in the infinite width limit as Gaussian processes
• A Quantitative Functional Central Limit Theorem for Shallow Neural Networks
• On Stein's method for infinite-dimensional Gaussian approximation in abstract Wiener spaces

Cites work

• scientific article; zbMATH DE number 3327878 (Why is no real title available?)
• -Stable convergence of heavy-/light-tailed infinitely wide neural networks
• An improved second-order Poincaré inequality for functionals of Gaussian fields
• Analysis and geometry of Markov diffusion operators
• Approximation Theory and Harmonic Analysis on Spheres and Balls
• Approximation of Hilbert-valued gaussians on Dirichlet structures
• Approximation of stable law in Wasserstein-1 distance by Stein's method
• Bayesian learning for neural networks
• Convergence of stochastic processes
• Deep stable neural networks: large-width asymptotics and convergence rates
• Diffusion processes and heat kernels on metric spaces
• Eigenfunctions of the Laplacian on a Riemannian manifold
• Fluctuations of eigenvalues and second order Poincaré inequalities
• Functional approximations via Stein's method of exchangeable pairs
• Fundamentals of Stein's method
• Heat kernel and analysis on manifolds
• High-dimensional probability. An introduction with applications in data science
• Mean field analysis of neural networks: a central limit theorem
• Normal Approximation by Stein’s Method
• Normal approximations with Malliavin calculus. From Stein's method to universality
• Note on A. Barbour's paper on Stein's method for diffusion approximations
• On Stein's method for infinite-dimensional Gaussian approximation in abstract Wiener spaces
• On Stein's method for multivariate self-decomposable laws
• On equivalence of infinite product measures
• Random Fields and Geometry
• Random neural networks in the infinite width limit as Gaussian processes
• Sharp estimates of the spherical heat kernel
• Spectral stability of metric-measure Laplacians
• Stein's method for diffusion approximations
• Stein's method for multivariate Brownian approximations of sums under dependence
• Stein's method for rough paths
• Stein's method for the Poisson-Dirichlet distribution and the Ewens sampling formula, with applications to Wright-Fisher models
• Stein's method of exchangeable pairs in multivariate functional approximations
• Stein's method, Gaussian processes and palm measures, with applications to queueing
• Stein's method, smoothing and functional approximation
• Trainability and Accuracy of Artificial Neural Networks: An Interacting Particle System Approach
• UNIFORM BOUNDS FOR EIGENFUNCTIONS OF THE LAPLACIAN ON MANIFOLDS WITH BOUNDARY*

This page was built for publication: Gaussian random field approximation via Stein's method with applications to wide random neural networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6567398)