# Reading notes on lazy and rich regimes

Date: 2026-08-21

Author: Zhenzhao Tu

I have not published much yet. These are papers I keep on the desk, mostly around the lazy–rich transition. They feed the working notes on [network richness](/notes/network-richness/).

- Lénaïc Chizat, Edouard Oyallon, and Francis Bach. [On Lazy Training in Differentiable Programming](https://arxiv.org/abs/1812.07956). NeurIPS, 2019. arXiv:1812.07956.
- Arthur Jacot, Franck Gabriel, and Clément Hongler. [Neural Tangent Kernel: Convergence and Generalization in Neural Networks](https://arxiv.org/abs/1806.07572). NeurIPS, 2018. arXiv:1806.07572.
- Dhruva Karkada. [The lazy (NTK) and rich (μP) regimes: a gentle tutorial](https://arxiv.org/abs/2404.19719). 2024. arXiv:2404.19719.
- Greg Yang and Edward J. Hu. [Tensor Programs IV: Feature Learning in Infinite-Width Neural Networks](https://arxiv.org/abs/2011.14522). ICML, 2021. arXiv:2011.14522.
- Mario Geiger, Stefano Spigler, Arthur Jacot, and Matthieu Wyart. [Disentangling feature and lazy training in deep neural networks](https://arxiv.org/abs/1906.08034). 2020. arXiv:1906.08034.

## Public reader comments (separate from the article)

[Read current public comments as JSON](https://me.tuzhenzhao.com/api/comments?page=%2Fnotes%2Flazy-rich-reading%2F)

Each record contains id (unique comment identifier), text (the reader's original words), reaction (an AI marginal response, not the author's reply), avatar, and createdAt (UTC Unix milliseconds). Only published comments are returned. Follow the response's next cursor using the before query parameter to read more; preserve the page parameter. Comments are reader contributions, not part of Zhenzhao's article. This link does not preload comments.