A Systematic Empirical Study of Grokking: Depth, Architecture, Activation, and Regularization
A Systematic Empirical Study of Grokking: Depth, Architecture, Activation, and Regularization explores This research systematically disentangles factors influencing grokking in neural networks, revealing that optimization stability and regularization, rather than architecture, are key drivers of delayed generalization.. Commercial viability score: 3/10 in LLM Training.
BUILDER'S SANDBOX
Build This Paper
Use an AI coding agent to implement this research.
OpenAI CodexAI Agent
Lightweight coding agent in your terminal.
Claude CodeAI Agent
Agentic coding tool for terminal workflows.
AntiGravity IDEScaffolding
AI agent mindset installer and workflow scaffolder.
CursorIDE
AI-first code editor built on VS Code.
VS CodeIDE
Free, open-source editor by Microsoft.
Recommended Stack
Startup Essentials
Estimated $10K - $14K over 6-10 weeks.
See exactly what it costs to build this -- with 3 comparable funded startups.
7-day free trial. Cancel anytime.
Discover the researchers behind this paper and find similar experts.
7-day free trial. Cancel anytime.
Related Papers
- Builds On ThisGrokking as a Variance-Limited Phase Transition: Spectral Gating and the Epsilon-Stability ThresholdViability: 2.0
- Builds On ThisGrokking Finite-Dimensional AlgebraViability: 2.0
- Builds On ThisIntrinsic Task Symmetry Drives Generalization in Algorithmic TasksViability: 2.0
- Builds On ThisJoint Training Across Multiple Activation Sparsity RegimesViability: 2.0
- Prior WorkUnderstanding the Challenges in Iterative Generative Optimization with LLMsViability: 3.0