Portfolio item number 1
Short description of portfolio item number 1
Posts by Collection
portfolio
Portfolio item number 2
Short description of portfolio item number 2
publications
Debiased Causal Tree: Heterogeneous Treatment Effects Estimation with Unmeasured Confounding
NeurIPS2022
This paper proposes a new splitting rule for tree-based methods to estimate heterogeneous treatment effects in the presence of unmeasured confounding. Full paper available for download.
Caizhi Tang*, Huiyuan Wang* (co-first authors), Xinyu Li, Qing Cui, Ya-Lin Zhang, Feng Zhu, Longfei Li, Jun Zhou, and Linbo Jiang. "Debiased Causal Tree: Heterogeneous Treatment Effects Estimation with Unmeasured Confounding." Advances in Neural Information Processing Systems 35 (2022), 5628–5640. https://proceedings.neurips.cc/paper_files/paper/2022/hash/2526d439030a3af95fc647dd20e9d049-Abstract-Conference.html
Difference-in-Differences Meets Tree-Based Methods: Heterogeneous Treatment Effects Estimation with Unmeasured Confounding
ICML2023
This paper combines tree-based methods with difference-in-differences to estimate heterogeneous treatment effects in the presence of unmeasured confounding. Full paper available for download.
Caizhi Tang*, Huiyuan Wang* (co-first authors), Xinyu Li, Qing Cui, Longfei Li, and Jun Zhou. "Difference-in-Differences Meets Tree-Based Methods: Heterogeneous Treatment Effects Estimation with Unmeasured Confounding." Proceedings of the 40th International Conference on Machine Learning (2023), 33792–33803. https://proceedings.mlr.press/v202/tang23j.html
The Aggregation–Heterogeneity Trade-off in Federated Learning
COLT2023
This paper explores the learning limit for heterogeneous federated learning. Full paper available for download.
Xuyang Zhao, Huiyuan Wang, and Wei Lin. "The Aggregation–Heterogeneity Trade-off in Federated Learning." Proceedings of the 36th Annual Conference on Learning Theory (2023), 5478–5502. https://proceedings.mlr.press/v195/zhao23b.html
Heterogeneous Federated Learning on Arbitrary Graphs
Manuscript2023
This paper introduces FedADMM, a federated learning approach that accommodates heterogeneity in data distributions, communication patterns, and device availability at scale. Full paper available for download.
Wang, H., Zhao, X., & Lin, W. (2023). "Heterogeneous federated learning on arbitrary graphs." Manuscript.
Nonasymptotic Theory for Two-Layer Neural Networks: Beyond the Bias–Variance Trade-off
Manuscript2023
This paper provides unified statistical guarantees for both underparameterized and overparameterized two-layer ReLU networks and reproduces the double-descent phenomenon. Full paper available for download.
Wang, H., & Lin, W. (2023). "Nonasymptotic theory for two-layer neural networks: Beyond the bias–variance trade-off." Manuscript.
A Statistical Theory of Regularization-Based Continual Learning
ICML2024
Xuyang Zhao, Huiyuan Wang, Weiran Huang, and Wei Lin. "A Statistical Theory of Regularization-Based Continual Learning." Proceedings of the 41st International Conference on Machine Learning (2024), 61021–61039. https://proceedings.mlr.press/v235/zhao24n.html
Prometheus: Out-of-Distribution Fluid Dynamics Modeling with Disentangled Graph ODE
ICML2024
Download here
CARE: Large Precision Matrix Estimation for Compositional Data
JASA2025
This paper introduces a new method called CARE (composition adaptive regularized estimation) for estimating sparse precision matrices in high-dimensional compositional data, providing theoretical guarantees and demonstrating its effectiveness in inferring microbial ecological networks.
Shucong Zhang, Huiyuan Wang, and Wei Lin. "CARE: Large Precision Matrix Estimation for Compositional Data." Journal of the American Statistical Association: Theory and Methods 120(549) (2025), 305–317. https://doi.org/10.1080/01621459.2024.2335586
A Statistical Framework of Watermarks for Large Language Models: Pivot, Detection Efficiency and Optimal Rules
The Annals of Statistics2025
Xiang Li, Feng Ruan, Huiyuan Wang, Qi Long, and Weijie J. Su. "A Statistical Framework of Watermarks for Large Language Models: Pivot, Detection Efficiency and Optimal Rules." The Annals of Statistics 53(1) (2025), 322–351. Invited for presentation at the Annals of Statistics discussion session, Joint Statistical Meetings 2025. https://doi.org/10.1214/24-AOS2468
Negative-Control-Calibrated Difference-in-Difference Analyses: Addressing Unmeasured Confounding in RWD with Application to Racial/Ethnic Differences
npj Digital Medicine2025
Dazheng Zhang*, Bingyu Zhang*, Huiyuan Wang* (co-first authors), Yiwen Lu, Charles J. Wolock, Wenjie Hu, Linbo Wang, George Hripcsak, and Yong Chen. "Negative-Control-Calibrated Difference-in-Difference Analyses: Addressing Unmeasured Confounding in RWD with Application to Racial/Ethnic Differences." npj Digital Medicine 8(1) (2025), 452. https://www.nature.com/articles/s41746-025-01821-w
Robust Detection of Watermarks for Large Language Models under Human Edits
JRSS-B2026
Li, X., Ruan, F., Wang, H., Long, Q., & Su, W. J. (2026). "Robust Detection of Watermarks for Large Language Models under Human Edits." Journal of the Royal Statistical Society Series B: Statistical Methodology, 88(2), 491–515. https://doi.org/10.1093/jrsssb/qkaf056
Surrogate-Powered Inference: Regularization and Adaptivity
JASA2026
Jianmin Chen, Huiyuan Wang, Thomas Lumley, Xiaowu Dai, and Yong Chen. "Surrogate-Powered Inference: Regularization and Adaptivity." Journal of the American Statistical Association: Applications and Case Studies (Moderate Revision), 2026+. https://arxiv.org/abs/2512.21826
Collaborative Indirect Treatment Comparisons with Multiple Distributed Single-Arm Trials
JASA2026
Yuru Zhu, Huiyuan Wang, Haitao Chu, Yumou Qiu, and Yong Chen. "Collaborative Indirect Treatment Comparisons with Multiple Distributed Single-Arm Trials." Journal of the American Statistical Association: Theory and Methods (Revise and Resubmit), 2026+. https://arxiv.org/abs/2509.23664
MOSAiC: Multi-site One-Shot Aggregation of Compressed Risk Functions
JASA2026
Yong Chen, Yiwen Lu, Jingmei Qiu, Huiyuan Wang, and Yudong Wang. "MOSAiC: Multi-site One-Shot Aggregation of Compressed Risk Functions." Journal of the American Statistical Association: Applications and Case Studies (2026). Authors listed in alphabetical order. https://doi.org/10.1080/01621459.2026.2698025
talks
CARE: Large Precision Matrix Estimation for Compositional Data
Published:
Received the Second Prize at the Fourth National Academic Forum for Doctoral Students in Statistics, awarded by the Chinese Association for Applied Statistics.
Heterogeneous Federated Learning on a Graph
Published:
Efficient and Robust High-Dimensional Hypothesis Testing with Surrogate Outcomes
Published:
Augmented Targeted Trial Emulation
Published:
Calibrated Digital Twins: Improving RCT Analysis with Distributionally Shifted RWD
Published:
Negative Control-Calibrated Difference-in-Difference Analyses: Addressing Unmeasured Confounding in Real-World Data with Application to Quantifying the Impact of the Pandemic on Racial/Ethnic Differences
Published:
Efficient Inference for Distributed Data with Structural Missingness
Published:
Distributed Inference under Arbitrary Cross-Site Heterogeneity
Published:
teaching
Teaching experience 2
Workshop University 1, Department 2015
This is a description of a teaching experience. You can use markdown like any other post.
Statistical Foundations of Machine Learning
1900
- Wang, H., Lin, W. (2023). “Nonasymptotic theory for two-layer neural networks: Beyond the bias–variance trade-off.” Manuscript.
- Wang, H., Zhao, X.,Lin, W. (2023). “Heterogeneous federated learning on arbitrary graphs.” Manuscript.