Functional dimension of feedforward ReLU neural networks

DOI10.1016/J.AIM.2025.110636MaRDI QIDQ6889783zbMATH OpenFDO

Authors Elisenda Grigsby, Kathryn Lindsey, Robert Meyerhoff, Chenxi Wu

Publication date 4 December 2025

Published in Advances in Mathematics (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/J.AIM.2025.110636

zbMATH Keywords

geometric deep learningidentifiability of ReLU networksparameter space symmetries

Mathematics Subject Classification ID

PL-topology (57Q99) Artificial neural networks and deep learning (68T07)

Cites work

• Algorithmic determination of the combinatorial structure of the linear regions of ReLU neural networks
• An embedding of ReLU networks and an analysis of their identifiability
• Convex Polytopes
• Geometry of linear convolutional networks
• Global minima of overparameterized neural networks
• Introduction to Smooth Manifolds
• Loss landscapes and optimization in over-parameterized non-linear systems and neural networks
• On Transversality of Bent Hyperplane Arrangements and the Topological Expressiveness of ReLU Neural Networks
• Spurious valleys in one-hidden-layer neural network optimization landscapes
• Topological properties of the set of functions generated by neural networks of fixed size

Cited in

(1)

• Gradient flow in parameter space is equivalent to linear interpolation in output space

This page was built for publication: Functional dimension of feedforward ReLU neural networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6889783)