个人简介
李凌丰博士现任河套数学与交叉科学研究院（深圳）助理教授。在加入 HIMIS 之前，他在香港心脑血管健康工程中心担任副研究员，导师为陈汉夫教授（Prof. Raymond Chan）。他于2022年在香港浸会大学获得数学博士学位，导师为台雪成教授（Prof. Xue-Cheng Tai）和杨将教授。此外，他分别于罗格斯大学（Rutgers University）和中山大学获得金融数学硕士及应用数学学士学位。 他的研究方向主要集中在机器学习在科学计算中的应用以及神经网络的理论分析。此外，他在图像处理的变分模型领域（variational models）也拥有丰富的研究经验。其研究成果已发表于多个国际学术期刊，例如《Journal of Computational Physics》、《Journal of Scientific Computing》及《Communications in Computational Physics》。
研究兴趣
机器学习在科学计算中的应用
神经网络的泛化误差分析
教育经历
博士/2018-2022 香港浸会大学 专业：数学
硕士/2016-2018 罗格斯大学-新布朗斯维克分校 专业： 金融数学
本科/2012-2016 中山大学 专业： 数学与应用数学
工作经历
2026-至今 河套数学与交叉学科研究院（深圳） 助理教授
2022-2025 香港心脑血管健康工程研究中心 副研究科学家
荣誉奖项
2022 香港浸会大学亚坤研究生奖学金
出版物
已发表论文
1. Zhang, H., Li, L., Tai, X. C., & Chan, R. H. F. (2025). Parametrized sampling
for 3D blood simulation in deformable vessels using Physics-Informed Neural Networks. Journal of Computational and Applied Mathematics, 117197.
2. Zhang, K., Li, L., Liu, H., Yuan, J. & Tai, X. C. (2025). Deep convolutional
neural networks meet variational shape compactness priors for image segmentation.
Neurocomputing, 129395.
3. Tai, X. C., Liu, H, Chan, R. H. F., & Li, L. (2024). A mathematical explanation
of UNet. Mathematical Foundations of Computing.
4. Li, L., Tai, X. C., & Chan, R. H. F. (2024). A new method to compute the blood
flow equations using the physics-informed neural operator. Journal of Computational Physics, 113380.
5. Li, L., Tai, X. C., Yang, J., & Zhu, Q. (2024). A priori error estimate of deep
mixed residual method for elliptic PDEs. Journal of Scientific Computing, 98(2),
44.
6. Li, L., Tai, X. C., & Yang, J. (2022). Generalization error analysis of neural
networks with gradient based regularization. Communications in Computational
Physics, 32 (4), 1007-1038.
7. Tai, X., Li, L., & Bae, E. (2021). The Potts model with different piecewise
constant representations and fast algorithms: a survey. Handbook of Mathematical
Models and Algorithms in Computer Vision and Imaging: Mathematical Imaging
and Vision, 1-41.
8. Li, L., Luo, S., Tai, X. C., & Yang, J. (2021). A level set representation method for
N-Dimensional convex shape and applications. Communications in Mathematical
Research, 37(2), 180.
9. Li, L., Luo, S., Tai, X. C., & Yang, J. (2021). A new variational approach based
on level-set function for convex hull problem with outliers. Inverse Problems &
Imaging, 15(2), 315.
10. Li, L., Luo, S., Tai, X. C., & Yang, J. (2019). A variational convex hull algorithm.
In International Conference on Scale Space and Variational Methods in Computer
Vision (pp. 224-235). Springer, Cham.
科研基金
(2026-2028) 香港研资局优配研究金LU13300125，1,071,000港元，图神经网络的数学建模与分析（Co-Inverstigator）
专利
1. 李凌丰;台雪成;陈汉夫;张元亭（2023）血管信息预测方法、装置、设备及存储介质[CN117257244A]. 中国国家知识产权局.
2. 陈翰杰;吕良一;李凌丰;张元亭（2023）基于PPG信号确定血压的方法、装置、设备及存储介质[CN117257256A]. 中国国家知识产权局.
学术报告
1. Hong Kong Joint Universities Conference on Structured Matrices and Scientific
Computing, September 25 - September 28, 2025, Hong Kong, China
2. International Conference on Applied Mathematics, Hong Kong, China, May 28 -
June 1, 2024
3. Second Ph.D. Student Seminar in Computational and Applied Mathematics, Beijing, China, September 2 - September 4, 2019.
4. Seminars of Mathematical Theories and Methods in Image Processing and Analysis,
Shenzhen, China, July 19 - July 22, 2019.
5. Seventh International Conference on Scale Space and Variational Methods in Computer Vision, Hofgeismar, Germany, June 30 - July 4, 2019.
期刊审稿
SIAM Journal on Imaging Science, Journal of Mathematical Imaging and Vision, Inverse Problem & Imaging, Partial Differential Equations and Applications