About
- Contact info: zhushyu AT outlook.com
- New website: I could not access the old website, so just create this new one.
Bio
Shengyu Zhu has been an Associate Professor at the Institute of Computing Technology, Chinese Academy of Sciences since Oct., 2024. Previously he worked as a Researcher at the AI Lab of Ubiquant Investment, and before that, was a Principal Researcher at Huawei Noah’s Ark Lab where he led a team working on causality and machine learning. He received his M.S. degree in mathematics and Ph.D. degree in electrical and computer engineering from Syracuse University, NY, USA, in 2016 and 2017, respectively. He obtained his B.E. degree in electrical engineering from Beijing Institute of Technology. He received the All University Doctoral Prize from Syracuse University for research excellence in completed dissertations in 2018. He has published in several top-ranked journals and conferences, including IEEE Trans. Information Theory, IEEE Trans. Signal Processing, Biometrika, AIJ, ICLR, NeurIPS, UAI, etc. During his Ph.D., he workd on some problems from information theory and statistical signal processing. His current interests mainly focus on reasoning, causality and machine learning.
Selected Publications
- ZIN: When and how to learn invariance without environment partition?, NeurIPS, 2022
- Out-of-distribution generalization with causal invariant transformations, CVPR, 2022
- Asymptotically optimal one- and two-sample testing with kernels, IEEE Transactions on Information Theory, 2021
- Causal discovery with reinforcement learning, ICLR, 2020