[2207.08799] Hidden Progress in Deep Learning: SGD Learns Parities Near the Computational Limit

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

[2207.08799] Hidden Progress in Deep Learning: SGD Learns Parities Near the Computational Limit Skip to main content arXiv is now an independent nonprofit! Learn more × Search arXiv Press Enter to search · Advanced search --> Computer Science > Machine Learning arXiv:2207.08799 (cs) [Submitted on 18 Jul 2022 ( v1 ), last revised 15 Jan 2023 (this version, v3)] Title: Hidden Progress in Deep Learning: SGD Learns Parities Near the Computational Limit Authors: Boaz Barak , Benjamin L. Edelman , Surbhi Goel , Sham Kakade , Eran Malach , Cyril Zhang View a PDF of the paper titled Hidde

related reading

• The Little Book of Deep Learningfleuret.org
• The Scaling Hypothesis · Gwern.netgwern.net
• On neural scaling and the quanta hypothesisericjmichaud.com
• [2604.21691] There Will Be a Scientific Theory of Deep Learningarxiv.org
• Maybe I was too harsh on deep learning theory (three days ago) — LessWronglesswrong.com
• The Decade of Deep Learning | Leo Gaobmk.sh
• arxiv.org/pdf/1805.08522arxiv.org
• Thoughts on loss landscapes and why deep learning worksberen.io
• Deep learning as program synthesis — LessWronglesswrong.com
• Thoughts on Loss Landscapes and why Deep Learning works — LessWronglesswrong.com
• [2101.12176] On the Origin of Implicit Regularization in Stochastic Gradient Descentarxiv.org
• Statistical Mechanics of Deep Learningganguli-gang.stanford.edu