Jiaming Xu

Jiaming Xu is an Associate Professor at the Fuqua School of Business, Duke University, where he has been on the faculty since July 2018. Prior to joining Duke, he was an Assistant Professor at the Krannert School of Management, Purdue University (2016–2018). He also held a research fellowship at the Simons Institute for the Theory of Computing at University of California, Berkeley in 2016, and was a postdoctoral fellow in the Statistics Department at the Wharton School, University of Pennsylvania (2015). Dr. Xu received his Ph.D. in Electrical and Computer Engineering from the University of Illinois at Urbana-Champaign in 2014 under the supervision of Bruce Hajek. He earned his M.S. from University of Texas at Austin in 2011 and his B.E. from Tsinghua University in 2009. His research interests lie at the intersection of artificial intelligence, high-dimensional statistics, operations research, and information theory, with additional contributions to convex and non-convex optimization, queueing theory, and game theory. He is a recipient of the Simons-Berkeley Fellowship (2016) and the NSF CAREER Award (2022). At Duke, Dr. Xu teaches courses including Decision Models, Decision Analytics & Modeling, Modern Analytics, Transforming Tech Analytics, and Statistical Inference on Graphs. He has received the Excellence in Teaching Award in the MQM program three times.

Jiaming Xu is a professor at the Fuqua School of Business, Duke University, specializing in network science, high-dimensional statistical inference, optimization, information theory, and communications and networking. His research explores the intersection of statistical learning, network analysis, and information theory, with a focus on distributed machine learning, community detection, and random graph matching. Xu's work addresses challenges in statistical-computational tradeoffs, exact recovery thresholds, and the information-theoretic limits of clustering and submatrix localization. His publications include studies on Byzantine gradient descent, semidefinite programming for cluster recovery, and the Wyner model in cellular networks. His research contributes to understanding the theoretical and algorithmic foundations of data-driven inference in complex systems.