Quadratic Weak-to-Strong Generalization in Random Feature Networks via Random Matrix Theory
arXiv:2610.09044v1 Announce Type: new Abstract: Weak-to-strong generalization is the phenomenon where a strong student model trained with labels produced by a weak teacher model is able to generalize better than the teacher. In this paper, we study this phenomenon in two-layer random feature networ…
Read the full story at arXiv stat.ML ↗
Timeline · 1 report
- 2026-10-08 04:00 · arXiv stat.ML
Quadratic Weak-to-Strong Generalization in Random Feature Networks via Random Matrix Theory