Canalization Before Generalization: Grokking as a Dynamical Probe
cs.LG
Submitted: 2026-08-26
Updated: 2026-09-04
Comments: 21 pages, 10 figures
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets
- Circuit Synchronization Precedes Generalization: A Causal Precursor to 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: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks