Liyan Xie is an Assistant Professor at the Department of Industrial and Systems Engineering at the University of Minnesota. Previously, Liyan was an Assistant Professor at School of Data Science, The Chinese University of Hong Kong, Shenzhen. She received a PhD from School of Industrial and Systems Engineering in Georgia Institute of Technology in 2021 (advised by Yao Xie). Her research interests lie at the intersection of statistics, optimization, and machine learning, with a primary focus on sequential change detection, spatio-temporal data modeling, diffusion models, and their applications in engineering problems.

Education

Ph.D., Georgia Institute of Technology, Industrial Engineering 2021 
B.S., University of Science and Technology of China, Statistics, 2016

Statistical inference, optimization, and machine learning, with a particular focus on sequential change detection, diffusion models, and data-driven decision making under uncertainty

Visit Liyan Xie's Google Scholar page

Currently Teaching Courses

• IE3521

Honors and Awards

2020 Selected to participate in EECS Rising Stars Workshop 
2019 Runner up for INFORMS Computing Society Student Paper Prize 
2019 Finalist of INFORMS QSR Best Student Paper Award

Selected Publications

Liyan Xie, Yuchen Liang, Venugopal V. Veeravalli. “Distributionally Robust Quickest Change Detection using Wasserstein Uncertainty Sets.” International Conference on Artificial Intelligence and Statistics (AISTATS), 2024. 

Yidong Ouyang, Liyan Xie, and Guang Cheng. “Improving Adversarial Robustness by Contrastive Guided Diffusion Process.” International Conference on Machine Learning (ICML), 2023. 

Liyan Xie, Yao Xie, and George Moustakides. “Window-limited CUSUM for Sequential Change Detection.” IEEE Transactions on Information Theory, 2023. 

Minghe Zhang, Liyan Xie, and Yao Xie. “Spectral CUSUM for Online Network Structure Change Detection.” IEEE Transactions on Information Theory, 2023. 

Liyan Xie, Shaofeng Zou, Yao Xie, and Venugopal V. Veeravalli. “Sequential Change Detection: Classical Results and New Directions.” IEEE Journal on Selected Areas in Information Theory, 2021.