Large Deviations of Gaussian Neural Networks with ReLU activation

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autor principal: Vogel, Quirin
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911432443953152
author Vogel, Quirin
author_facet Vogel, Quirin
contents We prove a large deviation principle for deep neural networks with Gaussian weights and at most linearly growing activation functions, such as ReLU. This generalises earlier work, in which bounded and continuous activation functions were considered. In practice, linearly growing activation functions such as ReLU are most commonly used. We furthermore simplify previous expressions for the rate function and provide a power-series expansions for the ReLU case.
format Preprint
id arxiv_https___arxiv_org_abs_2405_16958
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Large Deviations of Gaussian Neural Networks with ReLU activation
Vogel, Quirin
Machine Learning
Probability
60F10, 68T07
We prove a large deviation principle for deep neural networks with Gaussian weights and at most linearly growing activation functions, such as ReLU. This generalises earlier work, in which bounded and continuous activation functions were considered. In practice, linearly growing activation functions such as ReLU are most commonly used. We furthermore simplify previous expressions for the rate function and provide a power-series expansions for the ReLU case.
title Large Deviations of Gaussian Neural Networks with ReLU activation
topic Machine Learning
Probability
60F10, 68T07
url https://arxiv.org/abs/2405.16958