Gaussian random field approximation via Stein's method with applications to wide random neural networks
From MaRDI portal
Publication:6567398
DOI10.1016/j.acha.2024.101668zbMath1541.60034MaRDI QIDQ6567398
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)
Stein's methodGaussian random fielddistributional approximationdeep neural networksLaplacian-based smoothing
Random fields (60G60) Central limit and other weak theorems (60F05) Artificial neural networks and deep learning (68T07)
Cites Work
- Unnamed Item
- Unnamed Item
- Fundamentals of Stein's method
- 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
- Approximation of stable law in Wasserstein-1 distance by Stein's method
- Stein's method for rough paths
- Fluctuations of eigenvalues and second order Poincaré inequalities
- Stein's method for diffusion approximations
- Diffusion processes and heat kernels on metric spaces
- Bayesian learning for neural networks
- Functional approximations via Stein's method of exchangeable pairs
- Approximation of Hilbert-valued gaussians on Dirichlet structures
- Stein's method of exchangeable pairs in multivariate functional approximations
- Stein's method for multivariate Brownian approximations of sums under dependence
- Stein's method for the Poisson-Dirichlet distribution and the Ewens sampling formula, with applications to Wright-Fisher models
- Sharp estimates of the spherical heat kernel
- On Stein's method for multivariate self-decomposable laws
- An improved second-order Poincaré inequality for functionals of Gaussian fields
- Mean field analysis of neural networks: a central limit theorem
- Spectral stability of metric-measure Laplacians
- On equivalence of infinite product measures
- Normal Approximations with Malliavin Calculus
- Eigenfunctions of the Laplacian on a Riemannian Manifold
- UNIFORM BOUNDS FOR EIGENFUNCTIONS OF THE LAPLACIAN ON MANIFOLDS WITH BOUNDARY*
- Normal Approximation by Stein’s Method
- High-Dimensional Probability
- Approximation Theory and Harmonic Analysis on Spheres and Balls
- Analysis and Geometry of Markov Diffusion Operators
- Trainability and Accuracy of Artificial Neural Networks: An Interacting Particle System Approach
- Random Fields and Geometry
- Convergence of stochastic processes
- Deep stable neural networks: large-width asymptotics and convergence rates
- Stein's method, smoothing and functional approximation
- Random neural networks in the infinite width limit as Gaussian processes
- Stein's method, Gaussian processes and palm measures, with applications to queueing
- -Stable convergence of heavy-/light-tailed infinitely wide neural networks
This page was built for publication: Gaussian random field approximation via Stein's method with applications to wide random neural networks