You will choose one of the following papers to read in-depth throughout the course. At the end of the semster, you will have a 30 minute oral examination on your understanding of the paper. (I will post a list of specific questions to prepare later in the semester.) See the syllabus for a detailed description of the assignment.
If you have a paper in mind that is not on this list, chat with me!
| Title | Topics | Authors | Venue | Link |
|---|---|---|---|---|
| Benign Overfitting in Linear Regression | benign overfitting | Peter L. Bartlett, Philip M. Long, Gábor Lugosi, Alexander Tsigler | Proceedings of the National Academy of Sciences, 2020 | |
| Gradient Descent Maximizes the Margin of Homogeneous Neural Networks | classification | Kaifeng Lyu, Jian Li | ICLR, 2020 | |
| Implicit Regularization of Random Feature Models | effective regularization | Arthur Jacot, Berfin Şimşek, Francesco Spadaro, Clément Hongler, Franck Gabriel | ICML, 2020 | |
| Kernel and Rich Regimes in Overparametrized Models | feature learning | Blake Woodworth, Suriya Gunasekar, Jason D. Lee, Edward Moroshko, Pedro Savarese, Itay Golan, Daniel Soudry, Nathan Srebro | CoLT, 2020 | |
| On Lazy Training in Differentiable Programming | infinite width | Lenaic Chizat, Edouard Oyallon, Francis Bach | NeurIPS, 2019 | |
| Gaussian Process Behaviour in Wide Deep Neural Networks | infinite width | Alexander G. de G. Matthews, Mark Rowland, Jiri Hron, Richard E. Turner, Zoubin Ghahramani | ICLR, 2018 | |
| Explaining Neural Scaling Laws | scaling laws | Yasaman Bahri, Ethan Dyer, Jared Kaplan, Jaehoon Lee, Utkarsh Sharma | Proceedings of the National Academy of Sciences, 2024 |