arxiv
PublishedJune 17, 2026 at 4:00 AM
—neutral
Noise-Driven Escape from Metastable Phases explains Grokking in Deep Neural Networks
Publisher summary· verbatim
arXiv:2606.17120v1 Announce Type: new Abstract: Deep neural networks (DNNs) exhibit first order phase transitions under variations of the L2 regularization strength, with each transition marking the onset of a new learnable feature. Below a critical regularization strength, all features are in princ
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
arxivEffects of sparsity and superposition on loss in simple autoencoders3harxivTowards Anomaly Detection on Relational Data3harxivPACT: Preserving Anchored Cores in Task-vectors for Model Merging3harxivMetaboNet-Bench: A Multi-modal Benchmark for Glucose Forecasting in Type 1 Diabetes3hThe Bubble Brief
WEEKLYRead AI insights every Tuesday — top movers, new releases, story of the week.
Originally published on arxiv ↗