International Conference on Machine Learning · 2024
Cited
12
Resume (English only)
Background
Currently an Assistant Professor at Yau Mathematical Sciences Center, Tsinghua University.
Research focuses on mathematical analysis and algorithm development in machine learning and scientific computing, spanning both data and physical sciences.
Ph.D. training was grounded in classical numerical methods for partial differential equations (PDEs), especially finite element methods (FEM) and multigrid methods.
Primary research objective is to explore deep learning models and algorithms through the lens of numerical PDEs and geometry, aiming to advance theoretical foundations, algorithmic strategies, and practical applications.
Main research themes include: mathematical analysis of deep neural networks (DNNs) from a finite element perspective; theory, algorithms, and applications for CNNs and Transformers inspired by multigrid structures; and learning of data with low-dimensional structures.