Ye He (何晔)

Publications

• Yuqing Wang, Ye He, and Molei Tao (2024). Evaluating the Design Space of Diffusion-based Generative Models. NeurIPS 2024. Link
• Ye He, Alireza Mousavi-Hosseini, Krishnakumar Balasubramanian, and Murat A. Erdogdu (2024). A separation in Heavy-tailed Sampling: Gaussian vs. Stable Oracles for Proximal Samplers. NeurIPS 2024. Link
• Ye He, Kevin Rojas, and Molei Tao (2024). Zeroth-Order Sampling Methods for Non-Log-Concave Distributions: Alleviating Metastability by Denoting Diffusion. NeurIPS 2024. Link
• Ye He, Krishnakumar Balasubramanian, and Promit Ghosal (2023). High-dimensional Scaling Limits and Fluctuations of Online Least-Squares SGD with smooth Covariance. Annals of Applied Probability. Link
• Alireza Mousavi-Hosseini, Tyler K. Farghly, Ye He, Krishnakumar Balasubramanian, and Murat A. Erdogdu (2023). Towards a Complete Analysis of Langevin Monte Carlo: Beyond Poincare inequality. COLT 2023. Link
• Ye He, Krishnakumar Balasubramanian, and Murat A. Erdogdu (2022). An analysis of Transformed Unadjusted Langevin Algorithm for Heavy-tailed Sampling. IEEE transactions on Information Theory. Link
• Ye He, Krishnakumar Balasubramanian, Bharath K. Sriperumbudur, and Jianfeng Lu (2022). Regularized Stein Variational Gradient Flow. Foundations of Computational Mathematics. Link
• Ye He, Tyler K. Farghly, Krishnakumar Balasubramanian, and Murat A. Erdogdu (2022). Mean-Square Analysis of Discretized Ito Diffusions for Heavy-Tailed Sampling. Journal of Machine Learning Research. Link
• Ye He, Krishnakumar Balasubramanian, and Murat A. Erdogdu (2020). On the Ergodicity, Bias and Asymptotic Normality of Randomized Midpoint Sampling Method. NeurIPS 2020 Link