Xiaocong Xu is an Assistant Professor in the Department of Statistics at the University of Pittsburgh. Previously, he was a Postdoctoral Research Associate at the Marshall School of Business at the University of Southern California from 2024 to 2026. He received his Ph.D. from the Hong Kong University of Science and Technology in 2024. His research interests broadly span random matrix theory and the mathematical and algorithmic foundations of high-dimensional statistics. He is also interested in the design and analysis of sequential decision-making methods under uncertainty, particularly in revenue management applications such as inventory control and dynamic pricing.
- Ph.D. in Mathematics, Hong Kong University of Science and Technology, 2024
Education & Training
- Qiyang Han and Xiaocong Xu. Gradient descent inference in empirical risk minimization. The Annals of Statistics, 54(3): 1232--1261, 2026.
- Qiyang Han and Xiaocong Xu. The distribution of ridgeless least squares interpolators. Journal of Machine Learning Research, 27(23): 1--94, 2026.
- Yingying Fan, Yuxuan Han, Jinchi Lv, Xiaocong Xu, and Zhengyuan Zhou. Precise asymptotics and refined regret of variance-aware UCB. Advances in Neural Information Processing Systems, 2025.
- Zhigang Bao, Qiyang Han, and Xiaocong Xu. A leave-one-out approach to approximate message passing. The Annals of Applied Probability, 35(4): 2716--2766, 2025.
- Zhigang Bao, Jaehun Lee, and Xiaocong Xu. Phase transition for the smallest eigenvalue of covariance matrices. Probability Theory and Related Fields, 192: 35--133, 2025.
High-dimensional statistical inference
Random matrix theory
Robust knockoffs inference
Statistical decision-making
