| 2025 | AISTATS | Learning Gaussian Multi-Index Models with Gradient Flow: Time Complexity and Directional Convergence. | Berfin Simsek, Amire Bendjeddou, Daniel Hsu |
| 2025 | ICLR | Loss Landscape of Shallow ReLU-like Neural Networks: Stationary Points, Saddle Escape, and Network Embedding. | Zhengqing Wu, Berfin Simsek, Franois Gaston Ged |
| 2024 | ICML | Learning Associative Memories with Gradient Descent. | Vivien Cabannes, Berfin Simsek, Alberto Bietti |
| 2024 | ICML | Expand-and-Cluster: Parameter Recovery of Neural Networks. | Flavio Martinelli, Berfin Simsek, Wulfram Gerstner, Johanni Brea |
| 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 |
| 2020 | ICML | Implicit Regularization of Random Feature Models. | Arthur Jacot, Berfin Simsek, Francesco Spadaro, Clment Hongler, Franck Gabriel |
| 2019 | ACSSC | Online Bounded Component Analysis: A Simple Recurrent Neural Network with Local Update Rule for Unsupervised Separation of Dependent and Independent Sources. | Berfin Simsek, Alper T. Erdogan |