How feature learning can improve neural scaling laws

DOI10.1088/1742-5468/ADEFB1MaRDI QIDQ7234642zbMATH OpenFDO

Authors Blake Bordelon, Alexander B. Atanasov, Cengiz Pehlevan

Publication date 28 April 2026

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

Full work available at URL https://doi.org/10.1088/1742-5468/ADEFB1

zbMATH Keywords

deep learningdynamics of random field systemslearning theorymachine learning

Mathematics Subject Classification ID

Statistical mechanics, structure of matter (82-XX)

Cites work

• 10.1162/153244303321897690
• Asymptotic learning curves of kernel methods: empirical data versus teacher–student paradigm
• Disentangling feature and lazy training in deep neural networks
• Explaining neural scaling laws
• Geometric compression of invariant manifolds in neural networks
• Infinite-width limit of deep linear neural networks
• Statistical field theory for neural networks

This page was built for publication: How feature learning can improve neural scaling laws

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7234642)