|
I'm a second-year Ph.D. student in Computer Science at UT Austin, where I am fortunate to be advised by Kevin Tian. Previously, I completed my B.A. in Computer Science at Boston University, where I worked with Edward Chien and Kristjan Greenewald on optimal transport for machine learning. I primarily work on logconcave sampling and data privacy. More broadly, I'm interested in problems at the intersection of theoretical computer science, high-dimensional statistics, probability theory, and machine learning. In summer 2026, I interned at A*STAR in Singapore, hosted by Atsushi Nitanda. Please feel free to reach out if you're interested in my work!CV / Google Scholar / Twitter
News
|
anminggu@cs.utexas.edu
|
|
Authors are ordered alphabetically unless they are not. The Tractability Landscape of Sampling with Inexact ScoresAnming Gu, Kevin Tian, Hubert Yang, Yusong Zhu [arXiv] Functional Stochastic Localization Anming Gu, Bobby Shi, Kevin Tian Conference on Learning Theory (COLT), 2026. [arXiv] [COLT] [video (Kevin)] Mirror Mean-Field Langevin Dynamics Anming Gu, Juno Kim International Conference on Machine Learning (ICML), 2026. [arXiv] [ICML] Differentially Private Wasserstein Barycenters Anming Gu, Sasidhar Kunapuli, Mark Bun, Edward Chien, Kristjan Greenewald [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 (ICLR), 2025. [arXiv] [ICLR] Partially Observed Trajectory Inference using Optimal Transport and a Dynamics Prior Anming Gu, Edward Chien, Kristjan Greenewald International Conference on Learning Representations (ICLR), 2025. Preliminary version in NeurIPS OPT workshop, 2024. [arXiv] [ICLR] [OPT workshop] [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 (TMLR), 2023. [arXiv] [TMLR] [code] |