Function space and critical points of linear convolutional networks

DOI10.1137/23m1565504MaRDI QIDQ6562372

Guido Montúfar, Vahid Shahverdi, Matthew Trager, Kathlén Kohn

Publication date: 26 June 2024

Published in: SIAM Journal on Applied Algebra and Geometry (Search for Journal in Brave)

zbMATH Keywords

neural networkcritical pointssemialgebraic set

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Singularities in algebraic geometry (14B05) Semialgebraic sets and related spaces (14P10) Surfaces and higher-dimensional varieties (14J99) Projective techniques in algebraic geometry (14N05) Birational geometry (14E99) Polynomial optimization (90C23)

Cites Work

• Secants, bitangents, and their congruences
• The global optimization geometry of shallow linear neural networks
• Basic Algebraic Geometry 2
• Learning deep linear neural networks: Riemannian gradient flows and convergence to global minimizers
• Geometry of Linear Convolutional Networks

This page was built for publication: Function space and critical points of linear convolutional networks