I am now a Postdoctoral Fellow in the Department of Statistics at Harvard University, under the supervision of Prof. Zheng (Tracy) Ke. I obtained my Ph.D. degree in Statistics at UC Davis, where I was fortunate to be co-advised by Prof. Krishna Balasubramanian and Prof. Wolfgang Polonik. Before coming to UC Davis, I received my Bachelor’s degree in Math at Fudan University, where I was advised by Prof. Lei Shi.

My current research interests lie at the intersection of three domains: statistical inference, machine learning, and generative models. To be precise, I focus on understanding the theoretical principles of:

• Nonparametric Statistical Inference and Estimation,
• Statistical Perspectives on Dense Associative Memories (Hopfield networks),
• Statistical Network analysis, with their applications to uncertainty quantification, machine learning, reinforcement learning, causal inference, and econometrics.

Recent News

• I am invited to give a talk on `From Smooth to Nonsmooth: Minimax Optimal Regression with Laplacian Eigenmaps’ at SIAM UQ26 minisymposium “Probabilistic Manifold Learning and Deep Embeddings for Uncertainty Quantification”, Mar 2026.
• I am invited to give a talk on `Smooth Dynamic Network Analysis’ at the JSM2025, Aug 2025.
• I will give a talk titled `On the nonasymptotic statistical inferences via stabilization theory of Gaussian approximation bounds’ at the 22nd INFORMS Applied Probability Society Conference at Georgia Institute of Technology from June 30th to July 3rd, 2025.
• Our recent work Gaussian and Bootstrap Approximation for Matching-based Average Treatment Effect Estimators is now avaible on Arxiv! Taking ATE as an example, we provide a general framework for non-asymptotic statistical inference via a local geometric concept called `stabilization’.
• I joined the Department of Statistics, Harvard University, on September 1, 2024, as a Postdoctoral Fellow.