Random ReLU neural networks as non-Gaussian processes

MaRDI QIDQ6982680zbMATH OpenFDO

Authors Rahul Parhi, Pakshal Bohra, Ayoub El Biari, M. Unser

Publication date 16 May 2025

Published in Journal of Machine Learning Research (JMLR) (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://jmlr.org/papers/v26/24-0737.html

zbMATH Keywords

Gaussian processesnon-Gaussian processesrandom initializationrandom neural networksstochastic processes

Mathematics Subject Classification ID

Gaussian processes (60G15) Generalized stochastic processes (60G20) Artificial neural networks and deep learning (68T07)

Cites work

• A Unified Formulation of Gaussian Versus Sparse Stochastic Processes—Part I: Continuous-Domain Theory
• An introduction to sparse stochastic processes
• Banach space representer theorems for neural networks and ridge splines
• Bayesian learning for neural networks
• Distributional extension and invertibility of the k-plane transform and its dual
• Fractional Brownian Motions, Fractional Noises and Applications
• Function-space optimality of neural architectures with multivariate nonlinearities
• Gaussian and sparse processes are limits of generalized Poisson processes
• Generalized random fields and Lévy's continuity theorem on the space of tempered distributions
• scientific article; zbMATH DE number 1639852 (Why is no real title available?)
• scientific article; zbMATH DE number 3115395 (Why is no real title available?)
• scientific article; zbMATH DE number 3169049 (Why is no real title available?)
• scientific article; zbMATH DE number 3872419 (Why is no real title available?)
• scientific article; zbMATH DE number 1022519 (Why is no real title available?)
• scientific article; zbMATH DE number 810475 (Why is no real title available?)
• scientific article; zbMATH DE number 1402217 (Why is no real title available?)
• scientific article; zbMATH DE number 3220706 (Why is no real title available?)
• scientific article; zbMATH DE number 3232443 (Why is no real title available?)
• scientific article; zbMATH DE number 3336407 (Why is no real title available?)
• scientific article; zbMATH DE number 3187905 (Why is no real title available?)
• La transformation de Laplace dans les espaces linéaires.
• Near-Minimax Optimal Estimation With Shallow ReLU Neural Networks
• On the continuity of characteristic functionals and sparse stochastic modeling
• Processus linéaires, processus généralisés
• Random neural networks in the infinite width limit as Gaussian processes
• RKHS approach to detection and estimation problems--IV: Non-Gaussian detection
• Scaling limits of solutions of linear stochastic differential equations driven by Lévy white noises
• Stationary random distributions
• Understanding neural networks with reproducing kernel Banach spaces
• Uniform asymptotic expansions at a caustic
• What Kinds of Functions Do Deep Neural Networks Learn? Insights from Variational Spline Theory

Cited in

(1)

• Compositional function spaces for deep learning

This page was built for publication: Random ReLU neural networks as non-Gaussian processes

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6982680)