Function space and critical points of linear convolutional networks

DOI10.1137/23M1565504MaRDI QIDQ6562372FDOQ6562372

Authors: Kathlén Kohn, Guido Montúfar, Vahid Shahverdi, Matthew Trager 

Publication date: 26 June 2024

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

Recommendations

• Geometry of linear convolutional networks
• Optimization Landscape of Neural Networks
• Approximation Analysis of Convolutional Neural Networks
• Theory of deep convolutional neural networks. II: Spherical analysis
• Convergence of deep convolutional neural networks

zbMATH Keywords

critical pointsneural networksemialgebraic set

Mathematics Subject Classification ID

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

Cites Work

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

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

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6562372)