Anming Gu

I'm a first-year Ph.D. student in Computer Science at the University of Texas, Austin, advised by Kevin Tian. Previously, I completed my B.A. in Computer Science at Boston University, where I was fortunate to work with Edward Chien and Kristjan Greenewald on applied optimal transport for machine learning.

I'm interested in optimal transport and its applications to log-concave sampling, robust statistics, and differential privacy. More broadly, I'm interested in problems at the intersection of probability theory, theoretical computer science, and machine learning.

CV  /  Scholar  /  Twitter

News
2025.08 Started my PhD at UT Austin
2025.04 Attended ICLR 2025 in Singapore
profile photo

anminggu at utexas dot edu
GDC 4.718C
2317 Speedway
Austin, TX 78712

Publications

(α-β) denotes alphabetical order, * denotes equal contribution

Differentially Private Wasserstein Barycenters
Anming Gu, Sasidhar Kunapuli, Edward Chien, Mark Bun, Kristjan Greenewald
In submission

Private Continuous-Time Synthetic Trajectory Generation via Mean-Field Langevin Dynamics
Anming Gu, Edward Chien, Kristjan Greenewald
In submission
arXiv

Mirror Mean-Field Langevin Dynamics
Anming Gu*, Juno Kim*
In submission
arXiv

Compute-Optimal LLMs Provably Generalize Better with Scale
Marc Anton Finzi, Sanyam Kapoor, Diego Granziol, Anming Gu, Christopher De Sa, J Zico Kolter, Andrew Gordon Wilson
International Conference on Learning Representations, 2025.
arXiv

Partially Observed Trajectory Inference using Optimal Transport and a Dynamics Prior
Anming Gu, Edward Chien, Kristjan Greenewald
International Conference on Learning Representations, 2025.
Preliminary version in OPT Workshop on Optimization for Machine Learning, 2024. [link]
arXiv / poster / code

k-Mixup Regularization for Deep Learning via Optimal Transport
Kristjan Greenewald, Anming Gu, Mikhail Yurochkin, Justin Solomon, Edward Chien
Transactions on Machine Learning Research, 2023.
arXiv / code

Template from Jon Barron's webpage