Relative stability toward diffeomorphisms indicates performance in deep nets*

DOI10.1088/1742-5468/ac98acOpenAlexW3169720560MaRDI QIDQ5055429

Alessandro Favero, Leonardo Petrini, Matthieu Wyart, Mario Geiger

Publication date: 13 December 2022

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

Full work available at URL: https://arxiv.org/abs/2105.02468

zbMATH Keywords

machine learningdeep learning

Mathematics Subject Classification ID

Statistical mechanics, structure of matter (82-XX)

Uses Software

• SIFT
• CIFAR
• ImageNet

Cites Work

• Landscape and training regimes in deep learning
• Geometric compression of invariant manifolds in neural networks
• When do neural networks outperform kernel methods?*
• Breaking the Curse of Dimensionality with Convex Neural Networks
• Statistical Physics of Fields
• On the information bottleneck theory of deep learning
• Disentangling feature and lazy training in deep neural networks
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item

This page was built for publication: Relative stability toward diffeomorphisms indicates performance in deep nets*