Statistics · Machine Learning · Probability

Garrett G. Wen

Ph.D. Candidate in Statistics and Data Science at Yale University

Ph.D. Candidate,
Department of Statistics and Data Science,
Yale University
Kline Tower,
219 Prospect Street,
New Haven, CT 06511
Email: gang.wen [@] yale [DOT] edu

About me

I am Gang (Garrett) Wen, a Ph.D. candidate in the Department of Statistics and Data Science at Yale University. My doctoral advisors are Prof. Theodor Misiakiewicz and Prof. Zhou Fan. I have also been advised by Prof. Weijie Su on research since 2021. My research develops mathematical foundations for modern machine learning, with an emphasis on high-dimensional phenomena.

I received an M.A. in Statistics from Yale University in December 2025 and a B.Sc. in Statistics from the School of Mathematical Sciences at Peking University in 2022. In Summer 2026, I was a Summer Research Associate at the Center for Computational Mathematics, Flatiron Institute.

Deep learning theory, non-convex optimization, and high-dimensional learning dynamics
High-dimensional statistics, probability theory, and random matrix theory
Generative AI, including language-model watermarking and synthetic data
Mechanism design for scientific evaluation and peer review

textGrain: Entropy-Calibrated Watermarking for Language Model Text. X. Li, G. Wen, X. Chen, Q. Long, A. Jain, F. Joly, M. Lam, Q. Song, W. Su (2026). Technical report accompanying OpenAI's October 5 announcement.
Dynamical mean-field limit and replica-symmetric free energy for the orthogonally-invariant SK model. Z. Fan^**, T. Misiakiewicz^**, L. Wang^**, G. G. Wen^** (2026). Submitted to The Annals of Probability.
The sharp SAT/UNSAT phase transition in random ellipsoid fitting. T. Misiakiewicz^**, G. G. Wen^** (2026). Submitted to The Annals of Probability.
When does Gaussian equivalence fail and how to fix it: Non-universal behavior of random features with quadratic scaling. G. G. Wen, H. Hu, Y. M. Lu, Z. Fan, T. Misiakiewicz (2025). Submitted to Mathematical Statistics and Learning.
Recommending Best Paper Awards via the Isotonic Mechanism. G. G. Wen, B. Su, N. Collina, Z. Deng, W. Su (2026). Accepted for publication in Journal of Machine Learning Research.

^** Authors are listed in alphabetical order.