Zhenyu Zhu
Fields of expertise
Statistical Machine Learning
Deep Learning Theory
Deep Learning Theory
Biography
Zhenyu is an ELLIS Ph.D. student supervised by Volkan Cevher at École Polytechnique Fédérale de Lausanne (EPFL) and co-supervised by Francesco Locatello at Amazon Web Services (AWS). Previously I obtained B.S. from USTC and M.S. from EPFL.Publications
Selected publications
| Zhenyu Zhu, Francesco Locatello, Volkan Cevher Advances in Neural Information Processing Systems (NeurIPS), 2023 |
Sample Complexity Bounds for Score-Matching: Causal Discovery and Generative Modeling |
| Jiayuan Ye, Zhenyu Zhu, Fanghui Liu, Reza Shokri, Volkan Cevher Advances in Neural Information Processing Systems (NeurIPS), 2023 |
Initialization Matters: Privacy-Utility Analysis of Overparameterized Neural Networks |
| Zhenyu Zhu, Fanghui Liu, Grigorios G Chrysos, Francesco Locatello, Volkan Cevher International Conference on Machine Learning (ICML), 2023 |
Benign Overfitting in Deep Neural Networks under Lazy Training |
| Zhenyu Zhu, Fanghui Liu, Grigorios G Chrysos, Volkan Cevher Advances in Neural Information Processing Systems (NeurIPS), 2022 |
Robustness in deep learning: The good (width), the bad (depth), and the ugly (initialization) |
| Zhenyu Zhu, Fanghui Liu, Grigorios G Chrysos, Volkan Cevher Advances in Neural Information Processing Systems (NeurIPS), 2022 |
Generalization Properties of NAS under Activation and Skip Connection Search |
| Yongtao Wu, Zhenyu Zhu, Fanghui Liu, Grigorios G Chrysos, Volkan Cevher Advances in Neural Information Processing Systems (NeurIPS), 2022 |
Extrapolation and Spectral Bias of Neural Nets with Hadamard Product: a Polynomial Net Study |
| Zhenyu Zhu, Fabian Latorre, Grigorios G Chrysos, Volkan Cevher International Conference on Learning Representations (ICLR), 2022. |
Controlling the Complexity and Lipschitz Constant improves polynomial nets |