Beyond Embedding Transfer: Component Roles in Grokking Transfer and Stability
cs.LG
Submitted: 2026-09-16
Updated: 2026-09-16
Comments: 15 pages, 5 figures, conference preprint
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Grokking modular arithmetic
- Towards Inferential Reproducibility of Machine Learning Research
- Gaussian Error Linear Units (GELUs)
- Post-Grokking Collapse at the Representation-Readout Interface in Muon-Trained Transformers
- Grokking as the Transition from Lazy to Rich Training Dynamics
- Towards Understanding Grokking: An Effective Theory of Representation Learning
- Progress measures for grokking via mechanistic interpretability
- Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets
- Explaining grokking through circuit efficiency
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