phenomenon · first seen 30 Oct 2026
two-layer ReLU network teacher-student model
Also: teacher-student setup
A setting where a student network learns to imitate a fixed teacher network to study learning dynamics and feature learning.
Mentions per week
PapersCodeDiscussion
Earliest sources
- Gradient Descent on Two ReLU Neurons: Global Landscape and Bifurcation DynamicsPapers · 30 Oct 2026 · Binghua Li, Mengzhe Li, Denny Wu, Tianhao Wang
Latest sources
- Gradient Descent on Two ReLU Neurons: Global Landscape and Bifurcation DynamicsPapers · 30 Oct 2026 · Binghua Li, Mengzhe Li, Denny Wu, Tianhao Wang