Interface of Data Science and Geometry

Director: Zhigang Yao

Zhigang Yao is an associate professor and tenured professor in the Department of Statistics and Data Science at the National University of Singapore. He is currently a visiting member of the Center for Mathematical Sciences and Applications at Harvard University, a visiting professor at YMSC at Tsinghua University, and has also visited universities such as the Ecole Polytechnique Fédérale de Lausanne (EPFL) in Switzerland as a Professeur invitée. His research interests include statistical inference of complex data. In recent years, he has focused on research on non-Euclidean statistics and low-dimensional manifold fitting. With the collaboration and help of Professor Shing-Tung Yau, Professor Yao is committed to promoting research in the new field of interaction between geometry and statistics. In recent years, Professor Yao and his collaborators have proposed methods and theories to redefine the principal flow/sub-manifold and principal boundary of traditional PCA on Riemannian manifolds, as well as new methods and theories for manifold fitting in the ambient space. These methods aim to address deficiencies in traditional statistical methods and theories by mining the geometric structures hidden in the data itself. Currently, these methods and theories have been gradually used in the analysis of large-scale data, including single-cell sequencing data and network data. Personal webpage https://zhigang-yao.github.io/