Geometric compression of invariant manifolds in neural networks

DOI10.1088/1742-5468/ABF1F3OpenAlexW3202748241WikidataQ111520781 ScholiaQ111520781MaRDI QIDQ3382321

Mario Geiger, Kevin Tyloo, Matthieu Wyart, Leonardo Petrini, Jonas Paccolat

Publication date: 21 September 2021

Published in: Journal of Statistical Mechanics: Theory and Experiment (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2007.11471

zbMATH Keywords

learning theorymachine learningdeep learning

Mathematics Subject Classification ID

Statistical mechanics, structure of matter (82-XX)

Related Items (1)

Relative stability toward diffeomorphisms indicates performance in deep nets*

Uses Software

• MnasNet

Cites Work

• MnasNet
• A mean field view of the landscape of two-layer neural networks
• Learning Theory and Kernel Machines
• The space of interactions in neural network models
• On the information bottleneck theory of deep learning
• Scaling description of generalization with number of parameters in deep learning
• Disentangling feature and lazy training in deep neural networks
• A jamming transition from under- to over-parametrization affects generalization in deep learning
• Training Neural Networks as Learning Data-adaptive Kernels: Provable Representation and Approximation Benefits

This page was built for publication: Geometric compression of invariant manifolds in neural networks