Mapping the Emergence of Regularization-Driven Dynamics in Grokking

arXiv:2608.25813 · cs.LG · Submitted 2026-08-26 · Read on arXiv

cs.LG

Submitted: 2026-08-26

Updated: 2026-10-06

Comments: 21 pages, 10 figures

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Generalization — 116× in this paper · explained in 13 episodes
• Accuracy — 47× in this paper · explained in 1 episode
• Adam — 2× in this paper · explained in 2 episodes
• AdamW Optimizer — 2× in this paper · explained in 1 episode
• Loss Function — 2× in this paper · explained in 2 episodes
• Alignment — 1× in this paper · explained in 1 episode
• Computational Biology — 1× in this paper · explained in 2 episodes
• Data Augmentation — 1× in this paper · explained in 7 episodes
• Dynamical regimes — 1× in this paper · explained in 2 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Generative Model — 1× in this paper · explained in 2 episodes
• Generative Models — 1× in this paper · explained in 2 episodes
• Interpretability — 1× in this paper · explained in 15 episodes
• Non-stationarity — 1× in this paper · explained in 2 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Representation Learning — 1× in this paper · explained in 2 episodes
• Steering — 1× in this paper · explained in 2 episodes
• Transformer — 1× in this paper · explained in 2 episodes
• Verification — 1× in this paper · explained in 2 episodes

Sources

• Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets
• Learned Structure Shows Up Earlier in the Task's Own Basis: A Controlled Look at a Synchronisation Precursor in Grokking
• Thermodynamic Weight Decay: Exploring Grokking Acceleration via Attention Specific Heat
• The Weight Norm Sets the Grokking Timescale: A Causal Delay Law
• Thermodynamic Irreversibility of Training Algorithms

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks