# Quadratic Weak-to-Strong Generalization in Random Feature Networks via Random Matrix Theory

arXiv: https://arxiv.org/abs/2610.09044 · HTML: https://mlsanity.com/paper/2610.09044/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 42 references that are in the map.
- First posted on arXiv 6 Oct 2026.

## Builds on (most cited first, 6 of 6)

- [A non-asymptotic theory of Kernel Ridge Regression: deterministic equivalents, test error, and GCV estimator](https://mlsanity.com/paper/2403.08938/) (2024)
- [The Eigenlearning Framework: A Conservation Law Perspective on Kernel Regression and Wide Neural Networks](https://mlsanity.com/paper/2110.03922/) (2021)
- [More is Better in Modern Machine Learning: when Infinite Overparameterization is Optimal and Overfitting is Obligatory](https://mlsanity.com/paper/2311.14646/) (2023)
- [Weak-to-Strong Generalization Even in Random Feature Networks, Provably](https://mlsanity.com/paper/2503.02877/) (2025)
- [On the (Non-)Robustness of Two-Layer Neural Networks in Different Learning Regimes](https://mlsanity.com/paper/2203.11864/) (2022)
- [Improved Scaling Laws via Weak-to-Strong Generalization in Random Feature Ridge Regression](https://mlsanity.com/paper/2603.05691/) (2026)

## Abstract (arXiv)

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 networks where the model strength is determined by its width. Using tools from random matrix theory, we derive deterministic equivalents for the population errors of an optimally trained teacher and a student trained with gradient flow. For ReLU activation and a pure spherical harmonic target, we obtain sharp asymptotics under a Gaussian universality assumption, showing a quadratic improvement: the student error scales as the square of the teacher error. These results attain the general lower bound of Medvedev at al (2025). We also analyze how the student behaves under more general stopping times and targets supported on multiple harmonic degrees, characterizing the regimes in which weak-to-strong generalization occurs and identifying the transition between quadratic, non-quadratic, and no improvement.