Research Interests

  1. Integrative data analysis: multi-task learning, meta-learning and transfer learning;

  2. Latent variable models and representation learning;

  3. Non-convex optimization and distributed optimization.

Papers and Preprints

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

2024

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

  • Distribution-Free Predictive Inference under Unknown Temporal Drift.
    Elise Handagger, Chengpiao Huangdagger, Kaizheng Wang (alpha-beta)
    arXiv preprint arXiv:2406.06516, 2024.      Code

  • Model Assessment and Selection under Temporal Distribution Shift.
    Elise Handagger, Chengpiao Huangdagger, Kaizheng Wang (alpha-beta)
    International Conference on Machine Learning, 2024.
    arXiv      Code

2023

  • A Stability Principle for Learning under Non-Stationarity.
    Chengpiao Huangdagger, 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

  • Learning Gaussian Mixtures Using the Wasserstein-Fisher-Rao Gradient Flow.
    Yuling Yan*, Kaizheng Wang*, Philippe Rigollet (* = equal contribution)
    Annals of Statistics 52(4): 1774-1795, 2024.
    arXiv

2022

  • Variable Clustering via Distributionally Robust Nodewise Regression.
    Kaizheng Wang, Xiao Xu, Xun Yu Zhou (alpha-beta)
    arXiv preprint arXiv:2212.07944, 2022.

  • Adaptive Data Fusion for Multi-Task Non-Smooth Optimization.
    Henry Lam, Kaizheng Wang, Yuhang Wudagger, Yichen Zhang (alpha-beta)
    arXiv preprint arXiv:2210.12334, 2022.

  • Discussion of ‘Vintage Factor Analysis with Varimax Performs Statistical Inference’ by Rohe & Zeng.
    Kaizheng Wang
    Journal of the Royal Statistical Society Series B: Statistical Methodology 85(4): 1068, 2023.

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

2021

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

  • Modern Data Modeling: Cross-Fertilization of the Two Cultures
    Jianqing Fan, Cong Ma, Kaizheng Wang, Ziwei Zhu (alpha-beta)
    Observational Studies 7 (1): 65-76, 2021.

2020

  • Comment on “A Tuning-Free Robust and Efficient Approach to High-Dimensional Regression”
    Jianqing Fan, Cong Ma, Kaizheng Wang (alpha-beta)
    Journal of the American Statistical Association 115 (532): 1720-1725, 2020.

  • 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

  • Efficient Clustering for Stretched Mixtures: Landscape and Optimality
    Kaizheng Wang, Yuling Yan, Mateo Díaz
    Neural Information Processing Systems, 2020.
    arXiv

2019

  • Communication-Efficient Accurate Statistical Estimation
    Jianqing Fan, Yongyi Guo, Kaizheng Wang (alpha-beta)
    Journal of American Statistical Association 118 (542): 1000-1010, 2023.
    arXiv

2018

  • Robust High Dimensional Factor Models with Applications to Statistical Machine Learning
    Jianqing Fan, Kaizheng Wang, Yiqiao Zhong, Ziwei Zhu (alpha-beta)
    Statistical Science 36 (2): 303-327, 2021.
    arXiv

2017

  • 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.
    Short version accepted by International Conference on Machine Learning, 2018.
    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

  • 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

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

2016

  • Factor-Adjusted Regularized Model Selection
    Jianqing Fan, Yuan Ke, Kaizheng Wang (alpha-beta)
    Journal of Econometrics 216 (1): 71-85, 2020.
    arXiv

2015

  • Stochastic Representations for the Wave Equation on Graphs and Their Scaling Limits
    Kaizheng Wang
    Journal of Mathematical Analysis and Applications 449 (1): 808-828, 2017.
    arXiv

2014

  • On the Neumann Problem for Harmonic Functions in the Upper Half Plane
    Kaizheng Wang
    Journal of Mathematical Analysis and Applications 419 (2): 839-848, 2014.

Note

  • Some Compact Notations for Concentration Inequalities and User-Friendly Results
    Kaizheng Wang
    arXiv preprint arXiv:1912.13463, 2019.