Xiuyuan Cheng, Professor

As an applied analyst, I develop theoretical and computational techniques to solve problems in high-dimensional statistics, signal processing and machine learning.

Contact Info:

Office Location:	120 Science Drive, 293 Physics Building, Durham, NC 27708
Email Address:
Web Page:	https://services.math.duke.edu/~xiuyuanc/

Teaching (Spring 2026):

• MATH 532.01, REAL ANALYSIS II Synopsis

  Gross Hall 304B, TuTh 10:05 AM-11:20 AM

• MATH 465.01, INTRO HIGH DIM DATA ANALYSIS Synopsis

  Gross Hall 103, TuTh 11:45 AM-01:00 PM

  (also cross-listed as COMPSCI 445.01, STA 465.01)

• MATH 765.01, INTRO HIGH DIM DATA ANALYSIS Synopsis

  Gross Hall 103, TuTh 11:45 AM-01:00 PM

Education:

Ph.D.

Princeton University

2013

Recent Publications   (More Publications)

1. Calder, J; Cheng, X; Oberman, A; Ruthotto, L, PDEs for machine learning, Research in Mathematical Sciences, vol. 12 no. 3 (September, 2025) [doi]
2. Li, R; Qu, R; Parisi, F; Strino, F; Lam, H; Stanley, JS; Cheng, X; Myung, P; Kluger, Y, Cluster-independent multiscale marker identification in single-cell RNA-seq data using localized marker detector (LMD)., Communications biology, vol. 8 no. 1 (July, 2025), pp. 1058 [doi]  [abs]
3. Qu, R; Cheng, X; Sefik, E; Stanley Iii, JS; Landa, B; Strino, F; Platt, S; Garritano, J; Odell, ID; Coifman, R; Flavell, RA; Myung, P; Kluger, Y, Gene trajectory inference for single-cell data by optimal transport metrics., Nature biotechnology, vol. 43 no. 2 (February, 2025), pp. 258-268 [doi]  [abs]
4. Xu, C; Cheng, X; Xie, Y, Computing high-dimensional optimal transport by flow neural networks, Proceedings of Machine Learning Research, vol. 258 (January, 2025), pp. 2872-2880  [abs]
5. Purohit, V; Repasky, M; Lu, J; Qiu, Q; Xie, Y; Cheng, X, Consistency Posterior Sampling for Diverse Image Synthesis, Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (January, 2025), pp. 28327-28336 [doi]  [abs]

Recent Grant Support

• CAREER: Learning of graph diffusion and transport from high dimensional data with low-dimensional structures, National Science Foundation, 2023/09-2028/08.      
• RTG: Training Tomorrow's Workforce in Analysis and Applications, National Science Foundation, 2021/07-2027/06.      
• Collaborative Reseach: Transferable, Hierarchical, Expressive, Optimal, Robust, Interpretable NETworks (THEORINET), National Science Foundation, 2020/09-2026/08.      
• Collaborative Reseach: Transferable, Hierarchical, Expressive, Optimal, Robust, Interpretable NETworks (THEORINET), Simons Foundation, 2020/09-2026/08.      
• Bridging Statistical Hypothesis Tests and Deep Learning for Reliability and Computational Efficiency, Georgia Tech Research Corporation, 2022/01-2025/12.      
• NSF-BSF: Group Invariant Graph Laplacians: Theory and Computations, National Science Foundation, 2020/07-2025/06.