Publications

Below * is used to denote alphabetical ordering or equal contribution.
Preprints

  • How Discrete and Continuous Diffusion Meet: Comprehensive Analysis of Discrete Diffusion Models via a Stochastic Integral Framework
    Yinuo Ren, Haoxuan Chen, Grant M. Rotskoff, Lexing Ying
    Submitted. [PDF] [arXiv]

  • Ensemble-Based Annealed Importance Sampling
    Haoxuan Chen, Lexing Ying
    Submitted. [PDF] [arXiv]

Conference Papers

  • Accelerating Diffusion Models with Parallel Sampling: Inference at Sub-Linear Time Complexity
    Haoxuan Chen*, Yinuo Ren*, Lexing Ying, Grant M. Rotskoff
    Advances in Neural Information Processing Systems (NeurIPS), 2024 (Spotlight). [PDF] [arXiv]

  • When can Regression-Adjusted Control Variates Help? Rare Events, Sobolev Embedding and Minimax Optimality
    Jose H. Blanchet*, Haoxuan Chen*, Yiping Lu*, Lexing Ying*
    Advances in Neural Information Processing Systems (NeurIPS), 2023. [PDF] [Conference Proceedings] [OpenReview] [arXiv]

  • Machine Learning For Elliptic PDEs: Fast Rate Generalization Bound, Neural Scaling Law and Minimax Optimality
    Yiping Lu, Haoxuan Chen, Jianfeng Lu, Lexing Ying, Jose H. Blanchet
    International Conference on Learning Representations (ICLR), 2022. [PDF] [OpenReview] [arXiv]
    Short version presented at NeurIPS 2021 Workshop on the Symbiosis of Deep Learning and Differential Equations (DLDE) as a Spotlight Talk.

Journal Papers

  • Physics-Informed Neural Operator for Learning Partial Differential Equations
    Zongyi Li, Hongkai Zheng, Nikola Kovachki, David Jin, Haoxuan Chen, Burigede Liu, Kamyar Azizzadenesheli, Anima Anandkumar
    ACM/IMS Journal of Data Science 1 (3), 1-27, 2024. [PDF] [Journal] [arXiv]
    Short version presented at ICML 2022 Workshop on Continuous Time Perspectives in Machine Learning as a Spotlight Talk.

Professional Services

Referee Service