Research

Research interests

  • High-dimensional statistics
  • Generative AI and reinforcement learning
  • Adaptive design and sequential estimation
  • Astrostatistics
  • Random matrix theory
  • PDEs and dynamical systems

Preprints

  • Convergence and Stability Analysis of Self-Consuming Generative Models with Heterogeneous Human Curation. Hongru Zhao, Jinwen Fu, and Tuan Pham. Preprint. Paper
  • On Validating Angular Power Spectral Models for the Stochastic Gravitational-Wave Background Without Distributional Assumptions. Sara Algeri, Xiangyu Zhang, Erik Floden, Hongru Zhao, Galin Jones, Vuk Mandic, and Jesse Miller. Submitted, Physical Review D (2025). Details
  • Allocation-Constrained Adaptive Design and Sequential Estimation: Theory and Application to Bradley–Terry–Davidson Models. Hongru Zhao. Submitted, Journal of Statistical Planning and Inference (2025). Details
  • Subspace Decompositions for Association Structure Learning in Multivariate Categorical Response Regression. Hongru Zhao, Aaron J. Molstad, and Adam J. Rothman. Preprint (2025) Details

Publications: Theory and Methodology

  • Globally-Optimal Greedy Active Sequential Estimation. Xiaoou Li, and Hongru Zhao. IEEE Transactions on Information Theory 71, no. 5 (2025): 3871–3924. Paper
  • Distributed Algorithms for High-Dimensional Statistical Inference and Structure Learning with Heterogeneous Data. Hongru Zhao, and Xiaotong Shen. Statistica Sinica (2025). Paper
  • Convergence Analysis and Trajectory Comparison of Gradient Descent for Overparameterized Deep Linear Networks. Hongru Zhao, Jinchao Xu. Transactions on Machine Learning Research (2024) Paper
  • Exponential stability of the linear KdV-BBM equation. Kangsheng Liu, Zhuangyi Liu, and Hongru Zhao. Discrete and Continuous Dynamical Systems-B 29, no. 3 (2024): 1206-1216. Paper
  • Limiting empirical spectral distribution for products of rectangular matrices. Yongcheng Qi, and Hongru Zhao. Journal of Mathematical Analysis and Applications 502, no. 2 (2021): 125237. Paper

Publications: Applications

  • Testing models for angular power spectra: A distribution-free approach. Sara Algeri, Xiangyu Zhang, Erik Floden, Hongru Zhao, Galin L. Jones, Vuk Mandic, and Jesse Miller. Physical Review D (2025). Paper