Kaizheng Wang

I am an assistant professor in the Department of Industrial Engineering and Operations Research and a member of the Data Science Institute at Columbia University. My research interests lie at the intersection of machine learning, statistics and optimization. E-mail: kaizheng.wang [@] columbia [DOT] edu Google Scholar Resume

Openings

I'm seeking highly motivated Ph.D. students with strong mathematical backgrounds and interests in machine learning, statistics and optimization.

News

• We (Cynthia Rush, Marco Avella Medina, and I) are organizing an Optimization and Statistical Learning Workshop on April 3-4. Registration is open here!

• New paper “Uncertainty Quantification for LLM-Based Survey Simulations” posted on arXiv.
  

• Postdoc Zhongyuan Lyu will join the University of Sydney Business School as a Lecturer (equivalent to US tenure-track Assistant Professor) of Business Analytics. Congratulations!.
  

• New paper “Transfer Learning of CATE with Kernel Ridge Regression” posted on arXiv.
  

• New paper “A Particle Algorithm for Mean-Field Variational Inference” posted on arXiv.
  

• New paper “Localized Exploration in Contextual Dynamic Pricing Achieves Dimension-Free Regret” posted on arXiv.
  

• I will be an Area Chair of ICML 2025 and a meta-reviewer of COLT 2025.
  

• New paper “Adaptive Transfer Clustering: A Unified Framework” posted on arXiv.
  

• Our paper “An \(\ell_p\) Theory of PCA and Spectral Clustering” received the 2024 Frontier of Science Award presented by the International Congress for Basic Science.
  

• Paper “Model Assessment and Selection under Temporal Distribution Shift” accepted by ICML 2024. Congratulations to undergraduate student Elise Han on her first paper!
  

• Our proposal on policy evaluation, transfer learning and the safety of autonomous vehicles got awarded the Data Science Institute Seed Fund by Columbia University.
  

• Our paper on implicit regularization in nonconvex statistical estimation received the SIAM Activity Group on Imaging Science Best Paper Prize.
  

• I will be an Area Chair of ICML 2024 and a meta-reviewer of COLT 2024.
  

• Our team (Chengpiao Huang, Yuhang Wu, and myself) won the Second Place Award in the 2023 INFORMS Blue Summit Supplies Data Challenge, along with a $1,000 cash prize. We also clinched the top spot in the two-week live test of pricing and forecasting with our own data integration techniques (Papers 1 and 2). Special thanks to the INFORMS Data Mining Society and Blue Summit Supplies for putting together this wonderful competition!
  

• Undergraduate student Yuhang Wu started his PhD at the Decision, Risk, and Operations (DRO) division at Columbia Business School. Congratulations!
  

• Undergraduate student Sara Zhao received the prestigious Stephen D. Guarino Memorial Award, which is made annually to one member of the senior class of IEOR. Congratulations!
  
  

Representative Publications

(\(\alpha\)-\(\beta\): author names are sorted alphabetically; \(\dagger\): student/postdoc supervised.)

• Uncertainty Quantification for LLM-Based Survey Simulations.
  Chengpiao Huang\(\dagger\), Yuhang Wu, Kaizheng Wang
  arXiv preprint arXiv:2502.17773, 2025.      Code
  
  

• Adaptive Transfer Clustering: A Unified Framework.
  Yuqi Gu, Zhongyuan Lyu\(\dagger\), Kaizheng Wang (\(\alpha\)-\(\beta\))
  arXiv preprint arXiv:2410.21263, 2024.      Code
  
  

• A Stability Principle for Learning under Non-Stationarity.
  Chengpiao Huang\(\dagger\), Kaizheng Wang (\(\alpha\)-\(\beta\))
  arXiv preprint arXiv:2310.18304, 2023.      Code
  
  

• Pseudo-Labeling for Kernel Ridge Regression under Covariate Shift.
  Kaizheng Wang
  Junior Researcher Award, 2024 ICSA China Conference.
  arXiv preprint arXiv:2302.10160, 2023.      Talk      Code
  
  

• Adaptive and Robust Multi-Task Learning
  Yaqi Duan, Kaizheng Wang (\(\alpha\)-\(\beta\))
  Annals of Statistics 51(5): 2015-2039, 2023.
  arXiv      Code
  
  

• Clustering a Mixture of Gaussians with Unknown Covariance
  Damek Davis, Mateo Díaz, Kaizheng Wang (\(\alpha\)-\(\beta\))
  Bernoulli, Accepted.
  arXiv preprint arXiv:2110.01602, 2021.
  
  

• An \(\ell_p\) Theory of PCA and Spectral Clustering
  Emmanuel Abbe, Jianqing Fan, Kaizheng Wang (\(\alpha\)-\(\beta\))
  Annals of Statistics 50(4): 2359-2385, 2022.
  Frontiers of Science Award in Mathematics, 2024 International Congress of Basic Science.
  Presented by Jianqing Fan at the IMS Le Cam Lecture at the 2021 Joint Statistical Meetings.
  arXiv
  
  

• Entrywise Eigenvector Analysis of Random Matrices with Low Expected Rank
  Emmanuel Abbe, Jianqing Fan, Kaizheng Wang, Yiqiao Zhong (\(\alpha\)-\(\beta\))
  Annals of Statistics 48(3): 1452-1474, 2020.
  arXiv
  
  

• Implicit Regularization in Nonconvex Statistical Estimation: Gradient Descent Converges Linearly for Phase Retrieval, Matrix Completion and Blind Deconvolution
  Cong Ma, Kaizheng Wang, Yuejie Chi, Yuxin Chen
  Foundations of Computational Mathematics 20 (3): 451–632, 2020.
  SIAM Activity Group on Imaging Science Best Paper Prize, 2024.
  arXiv
  
  

• Distributed Estimation of Principal Eigenspaces
  Jianqing Fan, Dong Wang, Kaizheng Wang, Ziwei Zhu (\(\alpha\)-\(\beta\))
  Annals of Statistics 47 (6): 3009-3031, 2019.
  arXiv
  
  

• Spectral Method and Regularized MLE are both Optimal for Top-K Ranking
  Yuxin Chen, Jianqing Fan, Cong Ma, Kaizheng Wang (\(\alpha\)-\(\beta\))
  Annals of Statistics 47 (4): 2204-2235, 2019.
  arXiv
  
  

Funding

Support from the following funding sources is gratefully acknowledged:

• National Science Foundation (NSF) Grant DMS-2210907. Title: “Statistical and Computational Tools for Analyzing High-Dimensional Heterogeneous Data”. Duration: Aug 2022 – Jul 2025. Role: PI.

• Columbia University Data Science Institute Seed Fund. Title: “Policy Evaluation with Transfer Learning: How to assess safety performance of self-driving cars in NYC?”. Duration: Mar 2024 - Feb 2025. Role: Co-PI.

Miscellaneous

My Erdös number is 3: Kaizheng Wang - Emmanuel Abbe - Noga Alon - Paul Erdös.