Xunpeng Huang

Ph.D. student of HKUST

I am a third-year Ph.D. student at HKUST, co-advised by Prof. Tong Zhang and Prof. Yang Xiang. I am furtunate work closely with Prof. Yi-an Ma (University of California San Diego) and Prof. Difan Zou (The University of Hong Kong). Before that, I got my M.sc. degree in School of Computer Science and Technology from University of Science and Technology of China supervised by Prof. Enhong Chen. Besides, I used to work at Bytedance AI Lab under Prof. Lei Li’s supervision. My current research interests are machine learning algorithms and theory including sampling algorithms, stochastic/nonconvex optimization and mean-field analysis.

news

Sep 1, 2021 I joined Statml group in HKUST.

selected publications

  1. NeurIPS
    Reverse Transition Kernel: A Flexible Framework to Accelerate Diffusion Inference
    Huang, Xunpeng, Zou, Difan, Dong, Hanze, Zhang, Yi, Ma, Yian, and Zhang, Tong
    In Annual Conference on Neural Information Processing Systems (NeurIPS) 2024, Best paper of ICML Workshop on Structured Probabilistic Inference & Generative Modeling 2024
  2. COLT
    Faster Sampling without Isoperimetry via Diffusion-based Monte Carlo
    Huang, Xunpeng, Zou, Difan, Dong, Hanze, Ma, Yian, and Zhang, Tong
    In Conference on Learning Theory (COLT) 2024
  3. ICML
    Faster Sampling via Stochastic Gradient Proximal Sampler
    Huang, Xunpeng, Zou, Difan, Ma, Yian, Dong, Hanze, and Zhang, Tong
    In International Conference on Machine Learning (ICML) 2024
  4. ICLR
    Reverse Diffusion Monte Carlo
    Huang, Xunpeng, Dong, Hanze, HAO, Yifan, Ma, Yian, and Zhang, Tong
    In International Conference on Learning Representations (ICLR) 2024