How a student becomes a teacher: learning and forgetting through spectral methods

DOI10.1088/1742-5468/AD1BEAMaRDI QIDQ6628793zbMATH OpenFDO

Authors Lorenzo Giambagli, Lorenzo Buffoni, Lorenzo Chicchi, Duccio Fanelli

Publication date 29 October 2024

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

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://doi.org/10.1088/1742-5468/AD1BEA

zbMATH Keywords

deep learningmachine learningnetwork reconstruction

Mathematics Subject Classification ID

Statistical mechanics, structure of matter (82-XX)

Cites work

• Deep learning
• Dynamics of stochastic gradient descent for two-layer neural networks in the teacher–student setup*
• The committee machine: computational to statistical gaps in learning a two-layers neural network

Cited in

(1)

• Turing patterns on discrete topologies: from networks to higher-order structures

This page was built for publication: How a student becomes a teacher: learning and forgetting through spectral methods

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6628793)