Understanding deep learning requires rethinking generalization

N/A

U NDERSTANDING DEEP LEARNING REQUIRES RE - THINKING GENERALIZATION Chiyuan Zhang∗ Samy Bengio Moritz Hardt Massachusetts Institute of Technology Google Brain Google Brain chiyuan@mit.edu bengio@google.com mrtz@google.com Benjamin Recht†…

saved by

• Klaudia U.
• Evie Hu

related reading

• 1412.0233arxiv.org
• nn-notes.pdfboris-hanin.github.io
• [1709.06560] Deep Reinforcement Learning that Mattersarxiv.org
• Just Ask for Generalization | Eric Jangevjang.com
• [2604.21691] There Will Be a Scientific Theory of Deep Learningarxiv.org
• [2503.02113] Deep Learning is Not So Mysterious or Differentarxiv.org
• [2605.01172] A Theory of Generalization in Deep Learningarxiv.org
• arxiv.org/pdf/1805.08522arxiv.org
• [2201.02177] Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasetsarxiv.org
• [1912.02178] Fantastic Generalization Measures and Where to Find Themarxiv.org
• [1706.04599] On Calibration of Modern Neural Networksarxiv.org
• Deep Learning is Not So Mysterious or Differentarxiv.org