معرفی
Jiaming Xu is an Associate Professor of Business Administration in the Decision Sciences area at Duke University's Fuqua School of Business, where he has been a faculty member since July 2018. He is also a Faculty Network Member of the Duke Institute for Brain Sciences. His academic journey includes positions as an Assistant Professor at Purdue University's Krannert School of Management (2016-2018), a Research Fellow at the Simons Institute for the Theory of Computing at UC Berkeley (2016), and a Postdoctoral Fellow at the Statistics Department of the Wharton School at the University of Pennsylvania (2015).
- Ph.D. in Electrical and Computer Engineering from University of Illinois, Urbana-Champaign (2014)
- M.S. in Electrical and Computer Engineering from University of Texas, Austin (2011)
- B.S.E. in Electrical and Computer Engineering from Tsinghua University, China (2009)
Professor Xu's research focuses on developing fundamental methodologies for inferring information from data to enable downstream data-driven decision-making at scale. His work spans machine learning, networks, high-dimensional statistics, and information theory. He develops algorithms for improving decision-making efficiency under uncertainties and resource constraints while addressing emerging privacy and security issues. His research has significant implications for network data privacy, where he has demonstrated how anonymized data can still be used to re-identify individuals through unique behavioral patterns and network connections.
His recent publications reveal a strong focus on graph matching problems, community detection in networks, and privacy-preserving machine learning. Xu has made significant contributions to understanding information-theoretic thresholds in random graph matching, developing efficient algorithms for network alignment, and establishing fundamental limits for community detection. His work increasingly addresses the challenges of federated learning and privacy-preserving data analysis, reflecting the growing importance of these areas in both theoretical and practical contexts.
Scientific Awards and Recognition:
- NSF CAREER Award (2022) for Federated Learning: Statistical Optimality and Provable Security
- Simons-Berkeley Fellowship (2016)
- Excellence in Teaching Award in the MQM program (awarded twice)
Professor Xu has successfully mentored several students who have gone on to prestigious positions, including Sophie H. Yu (Assistant Professor at the Wharton School), Hanjing Zhu (Researcher at Amazon), Liren Yu (Researcher at Huawei), and Zhiyi Tian (Data Scientist at IQVIA). His research has been supported by multiple significant grants including an NSF CAREER award (2022-2027), a CIF Medium grant for Learning in Networks (2019-2023), and BIGDATA and CRII grants focused on network analysis and high-dimensional data (2018-2021).
At Duke, Professor Xu teaches Modern Analytics (Deep Learning), Decision Analytics & Modeling in the MQM program, and Decision Models in the MBA and WEMBA programs. His work bridges theoretical foundations with practical applications, particularly in the areas of network privacy and data security, where he has demonstrated how seemingly anonymized data can still be used to identify individuals through sophisticated matching algorithms.
