Profile picture placeholder
Administrative data

Zhenyu Zhu

zhenyu.zhu@epfl.ch https://zhuzhenyu1997.github.io/

Nationality: Chinese

EPFL › ETU › EDOC › EDIC

Expertise

Statistical Machine Learning
Deep Learning Theory
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 Institute of Science and Technology Austria (ISTA). Previously I obtained B.S. from University of Science and Technology of China (USTC) and M.S. from EPFL.

Selected publications

Sample Complexity Bounds for Score-Matching: Causal Discovery and Generative Modeling

Zhenyu Zhu, Francesco Locatello, Volkan Cevher
Published in Advances in Neural Information Processing Systems (NeurIPS), 2023 in

Initialization Matters: Privacy-Utility Analysis of Overparameterized Neural Networks

Jiayuan Ye, Zhenyu Zhu, Fanghui Liu, Reza Shokri, Volkan Cevher
Published in Advances in Neural Information Processing Systems (NeurIPS), 2023 in

Benign Overfitting in Deep Neural Networks under Lazy Training

Zhenyu Zhu, Fanghui Liu, Grigorios G Chrysos, Francesco Locatello, Volkan Cevher
Published in International Conference on Machine Learning (ICML), 2023 in

Robustness in deep learning: The good (width), the bad (depth), and the ugly (initialization)

Zhenyu Zhu, Fanghui Liu, Grigorios G Chrysos, Volkan Cevher
Published in Advances in Neural Information Processing Systems (NeurIPS), 2022 in

Generalization Properties of NAS under Activation and Skip Connection Search

Zhenyu Zhu, Fanghui Liu, Grigorios G Chrysos, Volkan Cevher
Published in Advances in Neural Information Processing Systems (NeurIPS), 2022 in

Extrapolation and Spectral Bias of Neural Nets with Hadamard Product: a Polynomial Net Study

Yongtao Wu, Zhenyu Zhu, Fanghui Liu, Grigorios G Chrysos, Volkan Cevher
Published in Advances in Neural Information Processing Systems (NeurIPS), 2022 in

Controlling the Complexity and Lipschitz Constant improves polynomial nets

Zhenyu Zhu, Fabian Latorre, Grigorios G Chrysos, Volkan Cevher
Published in International Conference on Learning Representations (ICLR), 2022. in