XIE, Yan
POSITION/TITLE
Associate Professor
Research Field
High-Performance Computing and AI-Enhanced Solvers for Partial Differential Equations
xieyan@sribd.cn
Education Background
2021-2026 Doctoral study, Academy of Mathematics and Systems Science, Chinese Academy of Sciences (Advisor: Prof. Chensong Zhang)
2024-2025 Visiting Student, The Chinese University of Hong Kong, Shenzhen
2017-2021 B.S. in Mathematics and Applied Mathematics, University of Chinese Academy of Sciences
2020 Visiting Student, National University of Singapore
Honors
MAJOR ACHIEVEMENTS / HONORS
1. PDE solvers validated in mechanics and microfluidics applications at scales up to 586 million DoFs.
2. MGCFNN published at ICLR 2025; high-frequency Helmholtz Schwarz work accepted to DD29.
3. Excellence Award, 2025 AMSS Dean's Scholarship.
Biography
Yan Xie is a Research Scientist at the Shenzhen Research Institute of Big Data (SRIBD). His research focuses on high-performance computing and AI-enhanced solvers for partial differential equations, including parallel iterative methods, domain decomposition, multigrid methods, and learning-based solvers. His work spans high-frequency Helmholtz/Maxwell equations, microfluidic Stokes flow, and contact-constrained mechanics, with an emphasis on scalable algorithms and large-scale applications.
Academic Publications
1. Y. Xie, M. Lv, C.-S. Zhang. MGCFNN: A Neural MultiGrid Solver with Novel Fourier Neural Network for High Wave Number Helmholtz Equations. ICLR 2025.
2. Y. Xie, S. Gong, I. G. Graham, E. A. Spence, C.-S. Zhang. Massively parallel Schwarz methods for the high frequency Helmholtz equation. Accepted to DD29.
3. Y. Xie, M. Lv, C.-S. Zhang. MGCNN: a learnable multigrid solver for sparse linear systems from PDEs on structured grids. Preprint, arXiv:2312.11093.
