Large deviations of one-hidden-layer neural networks

DOI10.1142/S0219493725500029MaRDI QIDQ7007628zbMATH OpenFDO

Authors Christian Hirsch

Publication date 26 March 2025

Published in Stochastics and Dynamics (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1142/S0219493725500029

zbMATH Keywords

artificial neural networksinteracting particle systemslarge deviationsstochastic gradient descentweak convergence

Mathematics Subject Classification ID

Ordinary differential equations and systems with randomness (34F05) Large deviations (60F10) Interacting random processes; statistical mechanics type models; percolation theory (60K35) Artificial neural networks and deep learning (68T07)

Cites work

• -Stable convergence of heavy-/light-tailed infinitely wide neural networks
• A mean field view of the landscape of two-layer neural networks
• A rigorous framework for the mean field limit of multilayer neural networks
• An Introduction to Banach Space Theory
• Analysis and approximation of rare events. Representations and weak convergence methods
• Asymptotic properties of one-layer artificial neural networks with sparse connectivity
• Empirical measure and small noise asymptotics under large deviation scaling for interacting diffusions
• Functional large deviations for Cox processes and \(Cox / G / \infty\) queues, with a biological application
• scientific article; zbMATH DE number 1713116 (Why is no real title available?)
• scientific article; zbMATH DE number 3951715 (Why is no real title available?)
• scientific article; zbMATH DE number 51724 (Why is no real title available?)
• scientific article; zbMATH DE number 1354815 (Why is no real title available?)
• scientific article; zbMATH DE number 1076323 (Why is no real title available?)
• scientific article; zbMATH DE number 1153603 (Why is no real title available?)
• scientific article; zbMATH DE number 1158743 (Why is no real title available?)
• Large deviation properties of weakly interacting processes via weak convergence methods
• Large deviations for Brownian particle systems with killing
• Mean Field Analysis of Deep Neural Networks
• Mean field analysis of neural networks: a central limit theorem
• Mean field analysis of neural networks: a law of large numbers
• Mean-field Langevin dynamics and energy landscape of neural networks
• Random measures, theory and applications
• Separability and completeness for the Wasserstein distance
• Sharp uniform-in-time propagation of chaos
• Trainability and Accuracy of Artificial Neural Networks: An Interacting Particle System Approach

Cited in

(2)

• LDP for the covariance process in fully connected Gaussian neural networks
• Large deviations of Gaussian neural networks with ReLu activation

This page was built for publication: Large deviations of one-hidden-layer neural networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7007628)