Ye He

17 papers A* 5Journal 12
YearRankTypeTitle / Venue / Authors
2026 J jnl
Diffusion Model's Generalization Can Be Characterized by Inductive Biases toward a Data-Dependent Ridge Manifold.
CoRR
Ye He, Yitong Qiu, Molei Tao
2026 J jnl
Finite-Particle Rates for Regularized Stein Variational Gradient Descent.
CoRR
Ye He, Krishnakumar Balasubramanian, Sayan Banerjee, Promit Ghosal
2025 J jnl
Regularized Stein Variational Gradient Flow.
Found. Comput. Math.
Ye He, Krishnakumar Balasubramanian, Bharath K. Sriperumbudur, Jianfeng Lu
2025 J jnl
Theory-Informed Improvements to Classifier-Free Guidance for Discrete Diffusion Models.
CoRR
Kevin Rojas, Ye He, Chieh-Hsin Lai, Yuhta Takida, Yuki Mitsufuji, Molei Tao
2025 J jnl
What Exactly Does Guidance Do in Masked Discrete Diffusion Models.
CoRR
Ye He, Kevin Rojas, Molei Tao
2024 A* conf
A Separation in Heavy-Tailed Sampling: Gaussian vs. Stable Oracles for Proximal Samplers.
NeurIPS
Ye He, Alireza Mousavi Hosseini, Krishnakumar Balasubramanian, Murat A. Erdogdu
2024 J jnl
An Analysis of Transformed Unadjusted Langevin Algorithm for Heavy-Tailed Sampling.
IEEE Trans. Inf. Theory
Ye He, Krishnakumar Balasubramanian, Murat A. Erdogdu
2024 A* conf
Evaluating the design space of diffusion-based generative models.
NeurIPS
Yuqing Wang, Ye He, Molei Tao
2024 J jnl
Evaluating the design space of diffusion-based generative models.
CoRR
Yuqing Wang, Ye He, Molei Tao
2024 J jnl
Mean-Square Analysis of Discretized Itô Diffusions for Heavy-tailed Sampling.
J. Mach. Learn. Res.
Ye He, Tyler Farghly, Krishnakumar Balasubramanian, Murat A. Erdogdu
2024 A* conf
Zeroth-Order Sampling Methods for Non-Log-Concave Distributions: Alleviating Metastability by Denoising Diffusion.
NeurIPS
Ye He, Kevin Rojas, Molei Tao
2024 J jnl
Zeroth-Order Sampling Methods for Non-Log-Concave Distributions: Alleviating Metastability by Denoising Diffusion.
CoRR
Ye He, Kevin Rojas, Molei Tao
2023 J jnl
Mean-Square Analysis of Discretized Itô Diffusions for Heavy-tailed Sampling.
CoRR
Ye He, Tyler Farghly, Krishnakumar Balasubramanian, Murat A. Erdogdu
2023 A* conf
Towards a Complete Analysis of Langevin Monte Carlo: Beyond Poincaré Inequality.
COLT
Alireza Mousavi Hosseini, Tyler K. Farghly, Ye He, Krishna Balasubramanian, Murat A. Erdogdu
2022 J jnl
Regularized Stein Variational Gradient Flow.
CoRR
Ye He, Krishnakumar Balasubramanian, Bharath K. Sriperumbudur, Jianfeng Lu
2020 A* conf
On the Ergodicity, Bias and Asymptotic Normality of Randomized Midpoint Sampling Method.
NeurIPS
Ye He, Krishnakumar Balasubramanian, Murat A. Erdogdu
2020 J jnl
On the Ergodicity, Bias and Asymptotic Normality of Randomized Midpoint Sampling Method.
CoRR
Ye He, Krishnakumar Balasubramanian, Murat A. Erdogdu