Ye He (何晔)

Applied mathematics for modern AI, sampling, and diffusion models.

I am a Hale Visiting Assistant Professor in the School of Mathematics at the Georgia Institute of Technology, hosted by Prof. Molei Tao. Before joining Georgia Tech, I received my Ph.D. in Mathematics from the University of California, Davis, advised by Prof. Krishna Balasubramanian .

My research focuses on the mathematical foundations of artificial intelligence, machine learning, and data science, with an emphasis on scalable inference methods, including sampling, diffusion models, and stochastic optimization.

Starting Fall 2026, I will be joining the Department of Applied Mathematics at the University of Colorado Boulder as a tenure-track Assistant Professor.

Download CV View publications
Portrait of Ye He

Publications

Selected papers in probability, sampling, and diffusion-based generative models.

  • Theory-Informed Improvements to Classifier-Free Guidance for Discrete Diffusion Models
    Kevin Rojas, Ye He, Chieh-Hsin Lai, Yuta Takida, Yuki Mitsufuji, and Molei Tao (2025).
    Preprint. Link
  • What Exactly Does Guidance Do in Masked Discrete Diffusion Models
    Ye He, Kevin Rojas, and Molei Tao (2025).
    Preprint. Link
  • Evaluating the Design Space of Diffusion-based Generative Models
    Yuqing Wang, Ye He, and Molei Tao (2024).
    NeurIPS 2024. Link
  • A separation in Heavy-tailed Sampling: Gaussian vs. Stable Oracles for Proximal Samplers
    Ye He, Alireza Mousavi-Hosseini, Krishnakumar Balasubramanian, and Murat A. Erdogdu (2024).
    NeurIPS 2024. Link
  • Zeroth-Order Sampling Methods for Non-Log-Concave Distributions: Alleviating Metastability by Denoting Diffusion
    Ye He, Kevin Rojas, and Molei Tao (2024).
    NeurIPS 2024. Link
  • High-dimensional Scaling Limits and Fluctuations of Online Least-Squares SGD with Smooth Covariance
    Krishnakumar Balasubramanian, Promit Ghosal, and Ye He (2024, authors listed alphabetically).
    Annals of Applied Probability. Link
  • Towards a Complete Analysis of Langevin Monte Carlo: Beyond Poincaré Inequality
    Alireza Mousavi-Hosseini, Tyler K. Farghly, Ye He, Krishnakumar Balasubramanian, and Murat A. Erdogdu (2023).
    COLT 2023. Link
  • An Analysis of Transformed Unadjusted Langevin Algorithm for Heavy-tailed Sampling
    Ye He, Krishnakumar Balasubramanian, and Murat A. Erdogdu (2022).
    IEEE Transactions on Information Theory. Link
  • Regularized Stein Variational Gradient Flow
    Ye He, Krishnakumar Balasubramanian, Bharath K. Sriperumbudur, and Jianfeng Lu (2022).
    Foundations of Computational Mathematics. Link
  • Mean-Square Analysis of Discretized Itô Diffusions for Heavy-Tailed Sampling
    Ye He, Krishnakumar Balasubramanian, and Murat A. Erdogdu (2022).
    Journal of Machine Learning Research. Link
  • On the Ergodicity, Bias and Asymptotic Normality of Randomized Midpoint Sampling Method
    Ye He, Krishnakumar Balasubramanian, and Murat A. Erdogdu (2020).
    NeurIPS 2020. Link

Teaching

Courses I have taught and assisted.

Summer 2019
MAT016C — Short Calculus , UC Davis
Fall 2023
MATH1553 — Introduction to Linear Algebra , Georgia Tech
Spring 2024
MATH2552 — Differential Equations , Georgia Tech

Contact

The best way to reach me is by email.

Email

yhe367@gatech.edu

Office

Skiles 016

Profiles

Google Scholar