[1805.08522] Deep learning generalizes because the parameter-function map is biased towards simple functions

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

[1805.08522] Deep learning generalizes because the parameter-function map is biased towards simple functions Skip to main content arXiv is now an independent nonprofit! Learn more × Search arXiv Press Enter to search · Advanced search --> Statistics > Machine Learning arXiv:1805.08522 (stat) [Submitted on 22 May 2018 ( v1 ), last revised 21 Apr 2019 (this version, v5)] Title: Deep learning generalizes because the parameter-function map is biased towards simple functions Authors: Guillermo Valle-Pérez , Chico Q. Camargo , Ard A. Louis View a PDF of the paper titled Deep learning ge

related reading

• arxiv.org/pdf/1805.08522arxiv.org
• [2503.02113] Deep Learning is Not So Mysterious or Differentarxiv.org
• Maybe I was too harsh on deep learning theory (three days ago) — LessWronglesswrong.com
• A Theory of Deep Learning | Elements of a Vector Spaceelonlit.com
• The Little Book of Deep Learningfleuret.org
• Just Ask for Generalization | Eric Jangevjang.com
• [2604.21691] There Will Be a Scientific Theory of Deep Learningarxiv.org
• Clare Lyle | What's grokking good for?clarelyle.com
• [1802.05296] Stronger generalization bounds for deep nets via a compression approacharxiv.org
• deeplearningbook.org/contents/ml.htmldeeplearningbook.org
• Theoretical Motivations for Deep Learning | Rinu Boneyrinuboney.github.io
• The Decade of Deep Learning | Leo Gaobmk.sh