[2504.18208v1] Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. arXiv Operational Status Get status notifications via email or slack

[2504.18208v1] Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime Skip to main content Search arXiv Press Enter to search · Advanced search --> Computer Science > Machine Learning arXiv:2504.18208v1 (cs) [Submitted on 25 Apr 2025 (this version), latest version 21 Jul 2025 ( v2 )] Title: Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime Authors: Raphaël Barboni (ÉNS-PSL), Gabriel Peyré (CNRS and ÉNS-PSL), François-Xavier Vialard (LIGM) View a PDF of the paper titled Ultra-fast feature l

related reading

• Deriving Muonjeremybernste.in
• [2604.21691] There Will Be a Scientific Theory of Deep Learningarxiv.org
• On neural scaling and the quanta hypothesisericjmichaud.com
• [2605.01172] A Theory of Generalization in Deep Learningarxiv.org
• Feature Visualizationdistill.pub
• [2304.03408] Dynamics of Finite Width Kernel and Prediction Fluctuations in Mean Field Neural Networksarxiv.org
• Greg Yang | Professional pagethegregyang.com
• Some Math behind Neural Tangent Kernel | Lil'Loglilianweng.github.io
• Maybe I was too harsh on deep learning theory (three days ago) — LessWronglesswrong.com
• NL.pdfabehrouz.github.io
• Understanding the Neural Tangent Kernel – EigenTaleseigentales.com
• The Little Book of Deep Learningfleuret.org