Songkai Xue
Home
Research
Teaching

Songkai Xue

alt text 

Welcome!

About me: I am a Ph.D. candidate in Statistics at the University of Michigan working with Professor Yuekai Sun and Professor Ji Zhu. Prior to joining Michigan, I completed my undergraduate studies at Peking University with a focus on mathematics and statistics.

Research interests: I am broadly interested in the mathematical foundations of data science. Some topics of my recent interests are

  • Fairness, Privacy, Robustness, and Interpretability in ML,

  • Learning under Distribution Shift,

  • Deep Learning Theory,

  • Statistical Network Analysis.

E-mail: sxue (at) umich.edu

Education

  • Ph.D. candidate, Statistics, University of Michigan, September 2020 - Present.

  • M.S., Applied Statistics, University of Michigan, May 2020.

  • B.S., Statistics, Peking University, July 2018.

Publications

  1. Calibrated data-dependent constraints with exact satisfaction guarantees.
    S. Xue, Y. Sun, and M. Yurochkin. NeuIPS 2022. [paper]

  2. How does overparametrization affect performance on minority groups?
    S. Maity, S. Roy, S. Xue, M. Yurochkin, and Y. Sun. Preprint. [paper]

  3. Statistical inference for individual fairness.
    S. Maity, S. Xue, M. Yurochkin, and Y. Sun. ICLR 2021. [paper] [slides]

  4. Auditing ML models for individual bias and unfairness.
    S. Xue, M. Yurochkin, and Y. Sun. AISTATS 2020. [paper] [slides]

  5. A flexible latent space model for multilayer networks.
    X. Zhang, S. Xue, and J. Zhu. ICML 2020. [paper]