Coca-Cola Foundation Chair and
Professor
Education
- Ph.D. Electrical Engineering (minor in Mathematics) (2012), Stanford University
- M.S. Electrical and Computer Engineering (2006), University of Florida
- B.S. Electrical Engineering and Information Science (2004), University of Science and Technology of China (USTC)
Expertise
- Statistics, Big Data
- Signal/Information Processing
- Machine Learning, Artificial Intelligence, Complex Systems
About
Yao Xie is the Coca-Cola Foundation Chair and Professor in the H. Milton Stewart School of Industrial and Systems Engineering at the Georgia Institute of Technology, and Associate Director of the Machine Learning Center (ML@GT). She received her Ph.D. in Electrical Engineering, with a minor in Mathematics, from Stanford University, and was previously a Research Scientist at Duke University.
Her research develops theory-grounded and computationally efficient methods for sequential inference and decision-making in high-dimensional and spatio-temporal settings, with an emphasis on change-point detection and uncertainty quantification. More recently, she has been integrating generative modeling and modern AI frameworks to enable robust inference and prediction in complex systems.
Her work has been recognized by the C. W. S. Woodroofe Award (2024) and the INFORMS Gaver Early Career Award (2022). She is also a Member of the 2026 Cohort of the National Academies’ New Voices in Sciences, Engineering, and Medicine program and the IEEE Information Theory Society Distinguished Lecturer for 2026–2027. She serves as an Associate Editor for IEEE Transactions on Information Theory, Journal of the American Statistical Association—Theory and Methods, The American Statistician, Operations Research, Annals of Applied Statistics, Sequential Analysis, and INFORMS Journal on Data Science, and as an Area Chair for NeurIPS, ICML, and ICLR, and a Senior Program Committee Member for AAAI.
Research
My research develops the statistical and computational foundations for sequential inference, high-dimensional change-point detection, and generative modeling for decision-making. I design principled methods for high-dimensional and spatio-temporal data that combine rigorous theoretical guarantees with scalable algorithms, supporting applications in public safety, power-grid resilience, and biomedical and health systems.
Teaching
My teaching philosophy emphasizes making rigorous statistical and machine learning concepts accessible, intuitive, and intellectually engaging by tightly integrating theory with applications. At the undergraduate level, I have taught Basic Statistics for junior students and developed and taught Foundations and Applications of Machine Learning for senior undergraduates, building strong foundations while connecting theory to real-world data problems. At the graduate level, I have taught Computational Data Analysis / Introduction to Machine Learning and Computational Statistics, with an emphasis on algorithmic thinking, statistical rigor, and hands-on implementation in Python. Across all courses, I design assignments and open-ended projects that combine theory with practice to foster critical thinking and independent problem solving, and I am deeply committed to mentoring students toward diverse career paths in academia, industry, and national laboratories.
Awards and Honors
- Member of Cohort 2026, New Voices in Sciences, Engineering, and Medicine Program, National Academies.
- IEEE Information Theory Society Distinguished Lecturer, 2026-2027.
- Executive Leadership in Academic Technology, Engineering, and Science (ELATES) Fellow, 2025-2026 Cohort.
- CWS Woodroofe Award, 2024.
- INFORMS Donald P. Gaver, Jr. Early Career Award for Excellence in Operations Research, 2022.
- INFORMS Daniel H. Wagner Prize for Excellence in the Practice of Advanced Analytics and Operations Research, Finalist, 2021.
- Georgia Tech Emerging Leaders Program, 2020.
- National Science Foundation CAREER Award, 2017.
- Georgia Tech Serve-Learn-Sustain Fellow, 2017.
- Class of 1969 Teaching Fellow, Georgia Tech, 2015.
- General Yao-Wu Wang Stanford Graduate Fellowship, 2007 - 2010
- Pan Wen Yuan Scholarship, 2007.
- University of Florida Alumni Fellowship, 2004-2006.
- Zhongzhi Zhang Science and Technology Scholarship, USTC 2003.
- Outstanding Student Scholarship of USTC, 2001-2003.
- First Prize, National Olympiad in Informatics in Provinces (NOIP), China, 1999.
Representative Publications
- Sinkhorn distributionally robust optimization.
Jie Wang, Rui Gao, Yao Xie.
Operations Research. 2025. - Convergence of flow-based generative models via proximal gradient descent in Wasserstein space.
Xiuyuan Cheng, Jianfeng Lu, Yixin Tan, and Yao Xie. (alphabetical)
IEEE Transactions on Information Theory. 2024. - Sequential predictive conformal inference for time series.
Chen Xu, Yao Xie.
ICML 2023. (journal version) IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2023. - Crime linkage detection by spatial-temporal-textual point processes.
Shixiang Zhu, Yao Xie.
Annals of Applied Statistics. Vol. 16, No. 2, pp. 1151-1170. 2022. - Nearly optimal adaptive procedure with change detection for piecewise-stationary bandit.
Yang Cao, Zheng Wen, Branislav Kveton, Yao Xie.
AISTATS 2019. - Poisson matrix recovery and completion.
Yang Cao, Yao Xie.
IEEE Transactions on Signal Processing, Vol. 64, No. 6, pp. 1609-1620, 2016. - Sequential multi-sensor change-point detection.
Yao Xie, David Siegmund.
Annals of Statistics, Vol. 41, No. 2, pp. 670-692, 2013.