Assistant Professor of Business Administration
Jiaming Xu is an Assistant Professor in the Decision Sciences area. His research focus is on the intersection of computation and statistics. Professor Xu seeks to understand the deep interplay between statistical optimality and computational complexity in high-dimensional statistical inference problems. He has been working on sharp performance analysis of semidefinite programming relaxations and belief propagation for community detection. Professor Xu teaches Decision Analytics and Modeling.
Appointments and Affiliations
- Assistant Professor of Business Administration
- Assistant Professor in the Department of Electrical and Computer Engineering
- Faculty Network Member of the Duke Institute for Brain Sciences
- Ph.D. University of Illinois, Urbana-Champaign, 2014
- M.S. University of Texas, Austin, 2011
- B.S.E. Tsinghua University (China), 2009
Network science, machine learning, high-dimensional statistical inference, information theory, optimization, stochastic systems, game theory, communications and networking
- BA 990: Selected Topics in Business
- DECISION 521Q: Decision Analytics and Modeling
- ECE 590: Advanced Topics in Electrical and Computer Engineering
- Chen, Y; Li, X; Xu, J, Convexified modularity maximization for degree-corrected stochastic block models, The Annals of Statistics, vol 46 no. 4 (2018) [10.1214/17-aos1595] [abs].
- Xu, J; Hajek, B; Wu, Y, Recovering a hidden community beyond the Kesten-Stigum threshold in O(|E|log*|V) time, Journal of Applied Probability, vol 55 no. 2 (2018), pp. 325-352 [abs].
- Banks, J; Moore, C; Vershynin, R; Verzelen, N; Xu, J, Information-Theoretic Bounds and Phase Transitions in Clustering, Sparse PCA, and Submatrix Localization, Ieee Transactions on Information Theory, vol 64 no. 7 (2018), pp. 4872-4894 [10.1109/tit.2018.2810020] [abs].
- Xu, J; Hajek, B; Wu, Y, Submatrix localization via message passing, Journal of Machine Learning Research, vol 18 no. 186 (2018), pp. 1-52 [abs].
- Hajek, B; Wu, Y; Xu, J, Information Limits for Recovering a Hidden Community, Ieee Transactions on Information Theory, vol 63 no. 8 (2017), pp. 4729-4745 [10.1109/tit.2017.2653804] [abs].