# A simple mean field model of feature learning

arXiv: https://arxiv.org/abs/2510.15174 · HTML: https://mlsanity.com/paper/2510.15174/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 34 references that are in the map.
- First posted on arXiv 16 Oct 2025.

## Builds on (most cited first, 22 of 22)

- [Neural Tangent Kernel: Convergence and Generalization in Neural Networks](https://mlsanity.com/paper/1806.07572/) (2018)
- [Prevalence of Neural Collapse during the terminal phase of deep learning training](https://mlsanity.com/paper/2008.08186/) (2020)
- [On Lazy Training in Differentiable Programming](https://mlsanity.com/paper/1812.07956/) (2018)
- [Deep Neural Networks as Gaussian Processes](https://mlsanity.com/paper/1711.00165/) (2017)
- [A Mean Field View of the Landscape of Two-Layers Neural Networks](https://mlsanity.com/paper/1804.06561/) (2018)
- [Mean-field theory of two-layers neural networks: dimension-free bounds and kernel limit](https://mlsanity.com/paper/1902.06015/) (2019)
- [Hidden Progress in Deep Learning: SGD Learns Parities Near the Computational Limit](https://mlsanity.com/paper/2207.08799/) (2022)
- [Neural Networks can Learn Representations with Gradient Descent](https://mlsanity.com/paper/2206.15144/) (2022)
- [Self-Consistent Dynamical Field Theory of Kernel Evolution in Wide Neural Networks](https://mlsanity.com/paper/2205.09653/) (2022)
- [Learning Single-Index Models with Shallow Neural Networks](https://mlsanity.com/paper/2210.15651/) (2022)
- [Learning Parities with Neural Networks](https://mlsanity.com/paper/2002.07400/) (2020)
- [Consistency and fluctuations for stochastic gradient Langevin dynamics](https://mlsanity.com/paper/1409.0578/) (2014)
- [A Theoretical Analysis on Feature Learning in Neural Networks: Emergence from Inputs and Advantage over Fixed Features](https://mlsanity.com/paper/2206.01717/) (2022)
- [Grokking as a First Order Phase Transition in Two Layer Networks](https://mlsanity.com/paper/2310.03789/) (2023)
- [Dynamics of Finite Width Kernel and Prediction Fluctuations in Mean Field Neural Networks](https://mlsanity.com/paper/2304.03408/) (2023)
- [Dynamical Decoupling of Generalization and Overfitting in Large Two-Layer Networks](https://mlsanity.com/paper/2502.21269/) (2025)
- [Learning sparse features can lead to overfitting in neural networks](https://mlsanity.com/paper/2206.12314/) (2022)
- [Local Kernel Renormalization as a mechanism for feature learning in overparametrized Convolutional Neural Networks](https://mlsanity.com/paper/2307.11807/) (2023)
- [Adaptive kernel predictors from feature-learning infinite limits of neural networks](https://mlsanity.com/paper/2502.07998/) (2025)
- [From Kernels to Features: A Multi-Scale Adaptive Theory of Feature Learning](https://mlsanity.com/paper/2502.03210/) (2025)
- [Wilsonian Renormalization of Neural Network Gaussian Processes](https://mlsanity.com/paper/2405.06008/) (2024)
- [Decoupling Dynamical Richness from Representation Learning: Towards Practical Measurement](https://mlsanity.com/paper/2410.04264/) (2024)

## Abstract (arXiv)

Feature learning (FL), where neural networks adapt their internal representations during training, remains poorly understood. Using methods from statistical physics, we derive a tractable, self-consistent mean-field (MF) theory for the Bayesian posterior of two-layer non-linear networks trained with stochastic gradient Langevin dynamics (SGLD). At infinite width, this theory reduces to kernel ridge regression, but at finite width it predicts a symmetry breaking phase transition where networks abruptly align with target functions. While the basic MF theory provides theoretical insight into the emergence of FL in the finite-width regime, semi-quantitatively predicting the onset of FL with noise or sample size, it substantially underestimates the improvements in generalisation after the transition. We trace this discrepancy to a key mechanism absent from the plain MF description: textitself-reinforcing input feature selection. Incorporating this mechanism into the MF theory allows us to quantitatively match the learning curves of SGLD-trained networks and provides mechanistic insight into FL.