arxiv
PublishedJune 2, 2026 at 4:00 AM
The Geometry of Grokking: Norm Minimization on the Zero-Loss Manifold
Publisher summary· verbatim
arXiv:2511.01938v3 Announce Type: replace-cross Abstract: Grokking is a puzzling phenomenon in neural networks where full generalization occurs only after a substantial delay following the complete memorization of the training data. Previous research has linked this delayed generalization to represe
Stay posted· Newsletter
A 5-min weekly brief — top movers, price watch, story of the week.
Discussion
No replies yet. Be first.
Related coverage
More from ARXIV
arxivFederatedSkill: Federated Learning for Agentic Skill Evolution7harxivToward a Modular Architecture for Embedded AI Agent Systems at the Edge7harxivA Graph Foundation Model with Spectral Parsing and Prototype-Guided Spatial Propagation7harxivAnomalies in Multivariate Time Series Benchmarks Are Mostly Univariate7hThe Bubble Brief
WEEKLYRead AI insights every Tuesday — top movers, new releases, story of the week.
Originally published on arxiv ↗