Hugging Face Trending Papers
Canalization Before Generalization: Grokking as a Dynamical Probe
Read the original on Hugging Face Trending Papers →The Flow has not summarised this story yet — read it at Hugging Face Trending Papers.
Related stories
arXiv Machine Learning
Aug 27
Canalization Before Generalization: Grokking as a Dynamical Probe
The paper investigates how overparameterized neural networks can fit training data in many different ways yet generalize differently. By applying short, fixed‑duration weight‑decay pulses during the grokking plateau, the authors show that early in training the pulses produce unordered shifts in generalization time, but later a clear dose ordering emerges: larger weight‑decay increases lead to earlier generalization, while larger decreases delay it. This ordering appears before visible generalization and persists even as test‑loss barriers collapse, a phenomenon the authors term the canalization of function selection.
arXiv AI
Jul 28
Grokking on the Weight-Decay Clock: A Rate Hierarchy from Softly Broken Symmetries
arXiv:2607. 23967v1 Announce Type: new Abstract: Delayed generalization, or grokking, remains poorly understood despite extensive empirical study.
arXiv Machine Learning
Jul 17
To Grok Grokking: Provable Grokking in Ridge Regression
arXiv:2601. 19791v4 Announce Type: replace Abstract: We study grokking, the onset of generalization long after overfitting, in a classical ridge regression setting.
arXiv Machine Learning
Sep 10
A Theoretical Analysis of Generalization Dynamics in Neural Networks under Gradient Descent with Weight Decay
arXiv:2609.07755v1 Announce Type: new Abstract: Understanding generalization remains a central challenge in machine learning because it requires jointly considering data, architecture, and training d...
arXiv Machine Learning
Jul 24
Thermodynamic Weight Decay: Exploring Grokking Acceleration via Attention Specific Heat
arXiv:2607. 20552v1 Announce Type: new Abstract: Grokking -- the delayed generalization of neural networks long after they have memorized their training data -- wastes thousands of training epochs and is notoriously unpredictable.
arXiv Machine Learning
Aug 24
Generalization Measures under Controlled Covariate Shift: A Regime-Aware Benchmark
arXiv:2602.01718v2 Announce Type: replace Abstract: Predicting generalization from quantities available before target-test evaluation remains a central challenge in deep learning. The systematic benc...