Yulian Wu (伍玉莲)
Division of Computer, Electrical, and Mathematical Sciences and Engineering (CEMSE)
King Abdullah University of Science and Technology
Thuwal, Saudi Arabia, 23955-6900
Email:yulian.wu@kaust.edu.sa
Bio
I am a third-year Ph.D. candidate in Computer Science at King Abdullah University of Science and Technology (KAUST). I am very fortunate to be advised by Prof.Francesco Orabona. Prior to this, I received my Master’s degree in Statistics under the supervision of Prof. Zhou Yu in 2021, and my Bachelor’s degree in Mathematics and Applied Mathematics in 2018 both at East China Normal University.
My research interests focus on bandits, reinforcement learning, and differential privacy. I’m also interested in quantum machine learning and trustworthy issues in bioinformatics.
Publications (* indicates equal contribution)[Google Scholar][DBLP]
-
PPML-Omics: a Privacy-Preserving federated Machine Learning system protects patients’ privacy from omic data.
Juexiao Zhou*, Siyuan Chen*, Yulian Wu*, Haoyang Li, Bin Zhang, Longxi Zhou, Yan Hu, Zihang Xiang, Zhongxiao Li, Ningning Chen, Wenkai Han, Di Wang and Xin Gao.
Science Advances
News: Inside Precision Medicine, Today Headline, Tech Xplore, ScienMag, Bioengineer.org, Newswise, EurekAlert, Biocompare, nabd.ws -
On Private and Robust Bandits.
Yulian Wu*, Xingyu Zhou*, Youming Tao and Di Wang.
The 37th Conference on Neural Information Processing Systems (NeurIPS 2023) -
Differentially Private Episodic Reinforcement Learning with Heavy-tailed Rewards.
Yulian Wu, Xingyu Zhou, Sayak Ray Chowdhury and Di Wang.
The 40th International Conference on Machine Learning (ICML 2023). -
Optimal Rates of (Locally) Differentially Private Heavy-tailed Multi-Armed Bandits.
Youming Tao*, Yulian Wu*, Peng Zhao and Di Wang.
The 25th International Conference on Artificial Intelligence and Statistics (AISTATS 2022).
Selected as an Oral paper (Acceptance Rate: 44/1685=2.6%).
CCS 2021 workshop on Privacy Preserving Machine Learning
ICML 2022 workshop on Responsible Decision Making in Dynamic Environments (Oral) -
Private Stochastic Convex Optimization and Sparse Learning with Heavy-tailed Data Revisited.
Youming Tao, Yulian Wu, Xiuzhen Cheng and Di Wang.
The 31st International Joint Conference on Artificial Intelligence (IJCAI 2022).
Preprints (* indicates equal contribution)
-
Better-than-KL PAC-Bayes Bounds.
Ilja Kuzborskij, Kwang-Sung Jun, Yulian Wu, Kyoungseok Jang and Francesco Orabona -
A Unified Approach to Differentially Private Heavy-tailed Multi-Armed Bandits.
Yulian Wu*, Youming Tao*, Xingyu Zhou and Di Wang -
Quantum Heavy-tailed Bandits.
Yulian Wu*, Chaowen Guan*, Vaneet Aggarwal and Di Wang -
Quantum Computing Provides Exponential Regret Improvement in Episodic Reinforcement Learning.
Bhargav Ganguly, Yulian Wu, Di Wang and Vaneet Aggarwal
Research Experience
-
King Abdullah University of Science and Technology (01/2021-08/2021)
Remote Research Intern
Supervisor: Prof. Di Wang -
Wayne State University (02/2022- 08/2023)
Remote Research Intern
Supervisor: Prof. Xingyu Zhou -
University at Buffalo, The State University of New York, Buffalo, USA (07/2022- 08/2022)
Visiting Student
Supervisor: Prof. Shaofeng Zou -
Microsoft Research Asia, Beijing, China (07/2023- 10/2023)
Onsite Research Intern
Mentor: Siwei Wang
Teachings
- Teaching Assistant of CS394Z: Introduction to Online Learning, Spring 2024 @KAUST
- Teaching Assistant of CS394V: Cont. Topics in Reinforcement Learning, Fall 2022 @KAUST
- Teaching Assistant of CS229: Machine Learning, Spring 2022, Spring 2023 @KAUST
- Teaching Assistant of Statistical Software: R Language, Spring 2020 @ECNU
Selected Awards
- NeurIPS Travel Award, 2023
- NIPS Grant by KAUST AI Initiative, 2022
- ICML Travel Award, 2022
- Outstanding Master’s Thesis of East China Normal University (Top 4% : 1/25), 2021
- Meritorious Winner of Interdisciplinary Contest in Modeling (ICM), 2016
Invited Talks
- Optimal Rates of (Locally) Differentially Private Heavy-tailed Multi-Armed Bandits. IJTCS-FAW 2022, Virtual
Services
- Program Committee member: SIGKDD 2023, SDM 2024
- Reviewer: ESORICS 2022, ECML-PKDD 2022, Euro S&P 2023, ECML-PKDD 2023, AISTATS 2024, SIGKDD 2024