唐科军
职务：助理教授
邮箱：tangkj@gbu.edu.cn
研究方向
u张量计算
u深度生成模型
u科学计算
u不确定性量化
主要成果
u在Journal of Computational Physics、Journal of Scientific Computing、SIAM Journal on Scientific Computing、ICLR 等计算数学期刊以及机器学习会议发表学术论文10篇
项目资助
u主持中国博士后科学基金面上项目，湖南省自然科学基金青年项目；
学习经历
u2015.09−2021.01 中国科学院大学（上海科技大学培养） 博士
u2011.09−2015.06 烟台大学 学士
工作经历
u2025.03−至今 大湾区大学（筹） 助理教授
u2024.11−2025.03 深圳理工大学 特聘副教授
u2023.02−2024.08 北京大学长沙计算与数字经济研究院 助理研究员/副研究员
u2021.02-2023.01 鹏城实验室 博士后
代表性论文
1．Kejun Tang, Xiaoliang Wan, and Chao Yang, DAS-PINNs: A deep adaptive sampling method for solving high-dimensional partial differential equations, Journal of Computational Physics 476 (2023): 111868.
2．Kejun Tang, Xiaoliang Wan, and Qifeng Liao, Adaptive deep density approximation for Fokker-Planck equations, Journal of Computational Physics, 457 (2022): 111080.
3．Kejun Tang and Qifeng Liao, Rank adaptive tensor recovery based model reduction for partial differential equations with high-dimensional random inputs, Journal of Computational Physics, 409 (2020): 109326.
4．Kejun Tang, Jiayu Zhai, Xiaoliang Wan, and Chao Yang, Adversarial Adaptive Sampling: Unify PINN and Optimal Transport for the Approximation of PDEs, The International Conference on Learning Representations (ICLR), 2024.
5．Xili Wang, Kejun Tang, Jiayu Zhai, Xiaoliang Wan, and Chao Yang, Deep adaptive sampling for surrogate modeling without labeled data, accepted by Journal of Scientific Computing, 101, 77 (2024).
6．Kejun Tang, Xiaoliang Wan, and Qifeng Liao, Deep density estimation via invertible block-triangular mapping, Theoretical and Applied Mechanics Letters, 10 (3), 143-148, 2020.
7．Pengfei Yin, Guangqiang Xiao, Kejun Tang and Chao Yang, AONN: An adjoint-oriented neural network method for all-at-once solutions of parametric optimal control problems, SIAM Journal on Scientific Computing, 46(1): C127-C153, 2024.
