Slower Generalization, Faster Memorization: A Sweet Spot in Algorithmic Learning
cs.LG
Submitted: 2026-05-14
Updated: 2026-11-03
Terminology
Sources
- Deep Learning Scaling is Predictable, Empirically
- Training Compute-Optimal Large Language Models
- Unified View of Grokking, Double Descent and Emergent Abilities: A Perspective from Circuits Competition
- Scaling Laws for Neural Language Models
- Teaching Arithmetic to Small Transformers
- Dichotomy of Early and Late Phase Implicit Biases Can Provably Induce Grokking
- How much do language models memorize?
- Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets
- Explaining grokking through circuit efficiency
- Critical Data Size of Language Models from a Grokking Perspective
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis