Cengiz Pehlevan
8
Papers
125
Total Citations
Papers (8)
Grokking as the transition from lazy to rich training dynamics
ICLR 2024arXiv
63
citations
Depthwise Hyperparameter Transfer in Residual Networks: Dynamics and Scaling Limit
ICLR 2024arXiv
45
citations
The Optimization Landscape of SGD Across the Feature Learning Strength
ICLR 2025arXiv
10
citations
A solvable model of learning generative diffusion: theory and insights
NeurIPS 2025arXiv
5
citations
No Free Lunch from Random Feature Ensembles: Scaling Laws and Near-Optimality Conditions
ICML 2025arXiv
2
citations
Do Mice Grok? Glimpses of Hidden Progress in Sensory Cortex
ICLR 2025
0
citations
Scaling Laws for Precision
ICLR 2025arXiv
0
citations
A Dynamical Model of Neural Scaling Laws
ICML 2024
0
citations