Prof. Fuqun Han received his bachelor’s degree in mathematics in 2018 and his PhD in mathematics in 2023, both from The Chinese University of Hong Kong. He then worked at the University of California, Los Angeles from 2023 to 2026 as a Hedrick Assistant Adjunct Professor. His research interests lie mainly in inverse problems, high-dimensional sampling, optimization, generative modeling, and their interconnections.
Previous Experience
- Jul 2023 - Jun 2026, Hedrick Assistant Adjunct Professor, UCLA.
Journal
- Han, Fuqun. , Osher, Stanley. & Li, Wuchen. (2026). Convergence of Noise-Free Sampling Algorithms with Regularized Wasserstein Proximals. Journal of Machine Learning Research. 27.
- Ning, Jianfeng. , Han, Fuqun. & Zou, Jun. (2025). A Direct Sampling Method and Its Integration with Deep Learning for Inverse Scattering Problems with Phaseless Data. SIAM Journal on Scientific Computing. 47. doi:10.1137/24M1642627
- Han, Fuqun. , Osher, Stanley. & Li, Wuchen. (2025). Tensor-Train-Based Sampling Algorithms for Approximating Regularized Wasserstein Proximal Operators. SIAM/ASA Journal on Uncertainty Quantification. 13. doi:10.1137/24M1633765
- Han, Fuqun. , Chow, Yat Tin. & Zou, Jun. (2022). A Direct Sampling Method for Simultaneously Recovering Elec- tromagnetic Inhomogeneous Inclusions of Different Nature. Journal of Computational Physics. 40. doi:10.1016/j.jcp.2022.111584
- Han, Fuqun. , Chow, Yat Tin. & Zou, Jun. (2021). A Direct Sampling Method for Simultaneously Recovering Inho- mogeneous Inclusions of Different Nature,. A Direct Sampling Method for Simultaneously Recovering Inhomogeneous Inclusions of Different Nature. 43. doi:10.1137/20M133628X
Last update date :
09 Jul 2026
