The geometry of the deep linear network

DOI10.1007/978-3-031-96118-2_1MaRDI QIDQ7232501zbMATH OpenFDO

Authors Govind Menon

Publication date 23 April 2026

Full work available at URL https://doi.org/10.1007/978-3-031-96118-2_1

zbMATH Keywords

Boltzmann entropydeep learningdeep linear networkdynamical systemsfree energyinvariant manifoldsRiemannian geometryRiemannian Langevin equationstochastic gradient descent

Mathematics Subject Classification ID

Diffusion processes and stochastic analysis on manifolds (58J65) Stochastic ordinary differential equations (aspects of stochastic analysis) (60H10) Applications of stochastic analysis (to PDEs, etc.) (60H30) Diffusion processes (60J60) Artificial neural networks and deep learning (68T07)

Cites work

• A mathematical theory of semantic development in deep neural networks
• Combinatorics and random matrix theory
• Completely integrable gradient flows
• Deep Linear Networks for Matrix Completion—an Infinite Depth Limit
• Function space and critical points of linear convolutional networks
• Geometry of linear convolutional networks
• scientific article; zbMATH DE number 3980094 (Why is no real title available?)
• scientific article; zbMATH DE number 43057 (Why is no real title available?)
• scientific article; zbMATH DE number 3554684 (Why is no real title available?)
• scientific article; zbMATH DE number 936519 (Why is no real title available?)
• scientific article; zbMATH DE number 3074339 (Why is no real title available?)
• Introduction to Riemannian Manifolds
• Learning deep linear neural networks: Riemannian gradient flows and convergence to global minimizers
• Morse Theory. (AM-51)
• Motion by mean curvature and Dyson Brownian motion
• Neural network approximation
• On the Bures-Wasserstein distance between positive definite matrices
• Stochastic analysis on manifolds
• The Principles of Deep Learning Theory

Cited in

(1)

• Modern and emerging phenomena in machine learning. Abstracts from the workshop held March 8--13, 2026

This page was built for publication: The geometry of the deep linear network

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7232501)