Title:  Sequentially Refined Latin Hypercube Designs with Flexibly and Adaptively Chosen Sample Sizes
Time: 10:00-11:00, August.25, 2024
Place: F310, School of Mechanical Engineering
Host:  LI Yongxiang. Assoc. Professor (Department of Industrial Engineering and Management)

Biography 
Dr. Xu He is currently an associate professor in Academy of Systems Science, Academy of Mathematics and Systems Science, Chinese Academy of Sciences. He received B.Sc. in Mathematics from the Peking University in 2007 and Ph.D. degree from the Dept. of Statistics at University of Wisconsin-Madison in 2012. His current research focuses on experimental design, design and analysis of computer experiments, and statistical methods for digital twins. He has published more than 10 papers in peer-reviewed journals, including Biometrika, Journal of the American Statistical Association, Annals of Statistics, etc.

Abstract
Latin hypercube designs are the most popular type of experimental design for computer experiments. Sequentially refined Latin hypercube designs are useful for computer experiments that are carried out in batches. In this work, we propose the first type of sequentially refined Latin hypercube designs that allow the size of subsequent batches to be flexibly chosen after completing former batches. Numerical results show our proposed designs are uniformly better than the preceding types of sequentially refined Latin hypercube designs for the problem of uncertainty quantification.