Geometry of Critical Sets and Existence of Saddle Branches for Two-layer Neural Networks

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Zhang, Leyang, Zhang, Yaoyu, Luo, Tao
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916263334248448
author Zhang, Leyang
Zhang, Yaoyu
Luo, Tao
author_facet Zhang, Leyang
Zhang, Yaoyu
Luo, Tao
contents This paper presents a comprehensive analysis of critical point sets in two-layer neural networks. To study such complex entities, we introduce the critical embedding operator and critical reduction operator as our tools. Given a critical point, we use these operators to uncover the whole underlying critical set representing the same output function, which exhibits a hierarchical structure. Furthermore, we prove existence of saddle branches for any critical set whose output function can be represented by a narrower network. Our results provide a solid foundation to the further study of optimization and training behavior of neural networks.
format Preprint
id arxiv_https___arxiv_org_abs_2405_17501
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Geometry of Critical Sets and Existence of Saddle Branches for Two-layer Neural Networks
Zhang, Leyang
Zhang, Yaoyu
Luo, Tao
Machine Learning
Optimization and Control
This paper presents a comprehensive analysis of critical point sets in two-layer neural networks. To study such complex entities, we introduce the critical embedding operator and critical reduction operator as our tools. Given a critical point, we use these operators to uncover the whole underlying critical set representing the same output function, which exhibits a hierarchical structure. Furthermore, we prove existence of saddle branches for any critical set whose output function can be represented by a narrower network. Our results provide a solid foundation to the further study of optimization and training behavior of neural networks.
title Geometry of Critical Sets and Existence of Saddle Branches for Two-layer Neural Networks
topic Machine Learning
Optimization and Control
url https://arxiv.org/abs/2405.17501