Computational and informational limits in high-dimensional statistical problems. Stanford University, 2024.

  • Yuhang Cai, Kangjie Zhou, Jingfeng Wu, Song Mei, Michael Lindsey, Peter Bartlett (2025). Implicit Bias of Gradient Descent for Non-Homogeneous Deep Networks. arXiv preprint.

  • Jingyang Lyu, Kangjie Zhou, Yiqiao Zhong (2025). A statistical theory of overfitting for imbalanced classification. arXiv preprint.

  • Shuangping Li*, Tselil Schramm*, Kangjie Zhou* (2024). Discrepancy Algorithms for the Binary Perceptron. The 57th Annual ACM Symposium on Theory of Computing (STOC 2025).

  • Andrea Montanari*, Kangjie Zhou* (2024). Which exceptional low-dimensional projections of a Gaussian point cloud can be found in polynomial time? arXiv preprint.

  • Fangyi Chen*, Yunxiao Chen*, Zhiliang Ying*, Kangjie Zhou* (2024). Dynamic Factor Analysis of High-dimensional Recurrent Events. To appear in Biometrika, 2025.

  • Yuchen Wu*, Kangjie Zhou* (2024). Sharp Analysis of Power Iteration for Tensor PCA. Journal of Machine Learning Research, 2024.

  • Andrea Montanari*, Yiqiao Zhong*, Kangjie Zhou* (2024). Tractability from overparametrization: The example of the negative perceptron. Probability Theory and Related Fields, 2024.

  • Raphaël Berthier*, Andrea Montanari*, Kangjie Zhou* (2023). Learning time-scales in two-layers neural networks. Foundations of Computational Mathematics, 2024.

  • Yuchen Wu*, Kangjie Zhou* (2023). Lower bounds for the convergence of tensor power iteration on random overcomplete models. The 36th Annual Conference on Learning Theory (COLT 2023).

  • Andrea Montanari*, Kangjie Zhou* (2022). Overparametrized linear dimensionality reductions: From projection pursuit to two-layer neural networks. arXiv preprint.

  • Kangjie Zhou, Andrea Montanari (2022). High-dimensional projection pursuit: Outer bounds and applications to interpolation in neural networks. The 35th Annual Conference on Learning Theory (COLT 2022).

  • Kangjie Zhou, Jinzhu Jia (2021). Propensity score adapted covariate selection for causal inference. arXiv preprint.


    * Alphabetical