Zijun Gao

Zijun Gao is a Ph.D. candidate in the Statistics Department at Stanford University advised by Professor Trevor Hastie. Prior to attending Stanford, she obtained a Bachelor of Science in Mathematics from Tsinghua University, China.

Her major research interest is causal inference with heterogeneity. Her works focus on developing efficient methodologies of estimating and validating heterogeneous causal effects with applications of large-scale healthcare databases. She also works on real-world data motivated topics such as conditional density estimation and batched bandit problem.

news

Feb 2, 2022 Our JMLR paper “LinCDE: Conditional Density Estimation via Lindsey’s Method” is now online!
Oct 9, 2021 R package LinCDE is released!
Sep 30, 2020 Zijun Gao receives Ric Weiland Graduate Fellowship!

selected publications

  1. DINA
    Estimating Heterogeneous Treatment Effects for General Responses
    Gao, Zijun, and Hastie, Trevor
    submitted to Journal of the Royal Statistical Society: Series B 2022
  2. LinCDE
    Conditional Density Estimation via Lindsey’s Method
    Gao, Zijun, and Hastie, Trevor
    Journal of Machine Learning Research 2022
  3. Assessment of heterogeneous treatment effect estimation accuracy via matching
    Gao, Zijun, Hastie, Trevor, and Tibshirani, Robert
    Statistics in Medicine 2021
  4. Minimax optimal nonparametric estimation of heterogeneous treatment effects
    Gao, Zijun, and Han, Yanjun
    Conference on Neural Information Processing Systems (NeurIPS) (Spotlight) 2020
  5. Batched multi-armed bandits problem
    Gao, Zijun, Han, Yanjun, Ren, Zhimei, and Zhou, Zhengqing
    Conference on Neural Information Processing Systems (NeurIPS) (Oral) 2019