| 2025 | ICLR | Shallow diffusion networks provably learn hidden low-dimensional structure. | Nicholas Matthew Boffi, Arthur Jacot, Stephen Tu, Ingvar M. Ziemann |
| 2025 | ICLR | How DNNs break the Curse of Dimensionality: Compositionality and Symmetry Learning. | Arthur Jacot, Seok Hoan Choi, Yuxiao Wen |
| 2025 | ICLR | Wide Neural Networks Trained with Weight Decay Provably Exhibit Neural Collapse. | Arthur Jacot, Peter Skenk, Zihan Wang, Marco Mondelli |
| 2024 | ICLR | Implicit bias of SGD in L2-regularized linear DNNs: One-way jumps from high to low rank. | Zihan Wang, Arthur Jacot |
| 2024 | ICML | Which Frequencies do CNNs Need? Emergent Bottleneck Structure in Feature Learning. | Yuxiao Wen, Arthur Jacot |
| 2023 | ICLR | Implicit Bias of Large Depth Networks: a Notion of Rank for Nonlinear Functions. | Arthur Jacot |
| 2021 | ICML | Geometry of the Loss Landscape in Overparameterized Neural Networks: Symmetries and Invariances. | Berfin Simsek, Franois Ged, Arthur Jacot, Francesco Spadaro, Clment Hongler, Wulfram Gerstner, Johanni Brea |
| 2021 | STOC | Neural tangent kernel: convergence and generalization in neural networks (invited paper). | Arthur Jacot, Franck Gabriel, Clment Hongler |
| 2020 | ICLR | The asymptotic spectrum of the Hessian of DNN throughout training. | Arthur Jacot, Franck Gabriel, Clment Hongler |
| 2020 | ICML | Implicit Regularization of Random Feature Models. | Arthur Jacot, Berfin Simsek, Francesco Spadaro, Clment Hongler, Franck Gabriel |