Zijian Guo

About me

I am a Qiushi Chair Professor (求是讲席教授) in the Center for Data Science at Zhejiang University. I received my B.S. in Mathematics from The Chinese University of Hong Kong in 2012 and my Ph.D. in Statistics from the University of Pennsylvania in 2017, where I was fortunate to be advised by Professor T. Tony Cai (COPSS Award laureate). From 2017 to 2025, I served on the faculty of the Department of Statistics at Rutgers University, advancing from Assistant Professor to tenured Associate Professor, before returning to China to join Zhejiang University in 2025.
“Qiushi” literally means “seeking truth,” echoing Zhejiang University’s motto “Seeking Truth and Pursuing Innovation.”

Research

My research develops statistical foundations for reliable and generalizable inference in modern data settings where classical assumptions often fail. I study how to make statistical conclusions stable and trustworthy under hidden confounding, invalid instruments, multi-source heterogeneity, distribution shift, and nonregularity.
My work spans four closely connected methodological areas: reliable causal inference under invalidity and hidden confounding, generalizable learning across heterogeneous sources, nonstandard inference beyond regular asymptotics, and high-dimensional uncertainty quantification. Across these areas, I use tools from optimization and machine learning to define robust statistical targets, design computable procedures, and develop valid uncertainty quantification when standard Wald-style approximations become unreliable. I am also interested in applications to genetics, proteomics, and multi-center health data, where robustness, transportability, and durable learning across heterogeneous environments are central.

Open Positions

• [Research Intern] We welcome research interns and assistants interested in causal inference, multi-source learning, robust optimization, and nonstandard inference. Strong preparation in probability, statistics, and scientific computing is welcome. Please check my research before applying.
• [PhD Applicant] If you would like to apply for a PhD at the Center for Data Science, Zhejiang University and work with me, please drop me an email with your CV and transcripts. Please check my research before applying.

News

• Apr 2026. Paper. Our paper "Distributionally Robust Learning for Multisource Unsupervised Domain Adaptation" (Wang, Z., Bühlmann, P., and Guo, Z.) has been accepted for publication in the Annals of Statistics, 20(1), 718–770.
• Mar 2026. Paper. Our paper "Robustness Against Weak or Invalid Instruments: Exploring Nonlinear Treatment Models with Machine Learning" (Guo, Z., Zheng, M., and Bühlmann, P.) has been accepted for publication in the Journal of Machine Learning Research.
• Mar 2026. Paper. Our paper "Decorrelated Local Linear Estimator: Inference for Non-linear Effects in High-dimensional Additive Models" (*Guo, Z., Yuan, W., and Zhang, C.) has been accepted for publication in the Journal of Machine Learning Research, 27(2026), 1-79. [Codes]
• Nov 2025. Paper. Our paper "Post-selection inference for causal effects after causal discovery" (Chang, T. H., Guo, Z., and Malinsky, D.) has been accepted for publication in the Biometrika, 113(1), asaf073.
• Nov 2024. Paper. Our paper "Robust Inference for Federated Meta-Learning" (Guo, Z., Li, X., Han, L., and Cai Tianxi) has been accepted for publication in the Journal of the American Statistical Association, 120(551), 1695-1710. [Codes]

Featured Publications

1. * Cai, T. T. and  Guo, Z. (2017).
   Confidence Intervals for High-Dimensional Linear Regression: Minimax Rates and Adaptivity.
   The Annals of Statistics, 45(2), 615-646. [Codes]

2. Guo, Z., Kang, H., Cai, T. T. and Small, D. S. (2018).
   Confidence Intervals for Causal Effects with Invalid Instruments using Two-Stage Hard Thresholding with Voting.
   Journal of the Royal Statistical Society: Series B, 80(4), 793-815. [Codes]

3. Guo, Z. , Cevid, D., and Bühlmann, P. (2022).
   Doubly Debiased Lasso: High-Dimensional Inference under Hidden Confounding.
   Annals of Statistics, 50 (3), 1320 - 1347. [Codes]

4. Guo, Z. (2023).
   Causal Inference with Invalid Instruments: Post-selection Problems and A Solution Using Searching and Sampling.
   Journal of the Royal Statistical Society: Series B (Statistical Methodology), 85(3), 959-985. [Codes]

5. Guo, Z. (2024).
   Statistical Inference for Maximin Effects: Identifying Stable Associations across Multiple Studies .
   Journal of the American Statistical Association, 119(547), 1968-1984. [Codes]

6. Yao, M., Miller, G., Vardarajan, B., Baccarelli, A., Guo, Z.^✉,and Liu, Z. ^✉(2024+).
   Deciphering proteins in Alzheimer’s disease: A new Mendelian randomization method integrated with AlphaFold3 for 3D structure prediction.  
   Cell Genomics, 4(12), 100700.

Selected Recent Preprints

1. Wang, Z.^#, Hu, Y.^#, Bühlmann, P., and Guo, Z.(2024).
   Causal Invariance Learning via Efficient Nonconvex Optimization
   Technical Report

2. Guo, Z., Wang, Z., Hu, Y., and Bach, F.(2025).
   Statistical Analysis for Conditional Group Distributionally Robust Optimization with Cross-Entropy Loss
   Technical Report

3. Zheng, M., Bonvini, M.^✉,and Guo, Z.^✉(2025).
   Perturbed Double Machine Learning: Nonstandard Inference Beyond the Parametric Length
   Technical Report

4. Koo, T. and Guo, Z. (2025).
   Distributionally Robust Synthetic Control: Ensuring Robustness Against Highly Correlated Controls and Weight Shifts.
   Technical Report

5. Heng, S.^#✉, Shen, Y.^#, Guo, Z.^✉ (2026).
   Propensity Score Propagation: A General Framework for Design-Based Inference with Unknown Propensity Scores.
   Technical Report

Honors and Awards

• ICSA Outstanding Young Researcher Award, 2023.

• Honorary mention for Bernoulli Society New Researcher Award, 2023.

• ICSA New Researcher Award, ICSA International Conference, 2019.

• IMS travel Award, JSM 2017.

• President Gutmann Leadership Award, University of Pennsylvania, 2017.

• J. Parker Brusk Prize, 2016.

• Section in Epidemiology Young Investigator Award, JSM 2013.

Contact

underline indicates supervised students ; # indicates equal contribution; * indicates alphabetical ordering ; ✉ indicates corresponding authorship.