An analytic theory of shallow networks dynamics for hinge loss classification*

DOI10.1088/1742-5468/ac3a76OpenAlexW3105547603MaRDI QIDQ5020044

Franco Pellegrini, Giulio Biroli

Publication date: 3 January 2022

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

Full work available at URL: https://arxiv.org/abs/2006.11209

zbMATH Keywords

machine learning

Mathematics Subject Classification ID

Statistical mechanics, structure of matter (82-XX)

Uses Software

• MNIST

Cites Work

• Unnamed Item
• Ginzburg-Landau vortices, Coulomb gases, and renormalized energies
• Universal approximation bounds for superpositions of a sigmoidal function
• A mean field view of the landscape of two-layer neural networks
• Statistical mechanical analysis of learning dynamics of two-layer perceptron with multiple output units
• Comparing dynamics: deep neural networks versus glassy systems
• Scaling description of generalization with number of parameters in deep learning
• Disentangling feature and lazy training in deep neural networks

This page was built for publication: An analytic theory of shallow networks dynamics for hinge loss classification*