Math @ Duke

Xiuyuan Cheng, Assistant Professor
As an applied analyst, I develop theoretical and computational techniques to solve problems in highdimensional statistics, signal processing and machine learning.  Contact Info:
 Education:
Ph.D.  Princeton University  2013 
 Recent Publications
(More Publications)
 Cheng, X; Cloninger, A; Coifman, RR, Twosample statistics based on anisotropic kernels,
Information and Inference
(December, 2019), Oxford University Press (OUP) [doi] [abs]
 Cheng, X; Rachh, M; Steinerberger, S, On the diffusion geometry of graph Laplacians and applications,
Applied and Computational Harmonic Analysis, vol. 46 no. 3
(May, 2019),
pp. 674688, Elsevier BV [doi]
 Cheng, X; Qiu, Q; Calderbank, R; Sapiro, G, RoTDCF: Decomposition of convolutional filters for rotationequivariant deep networks,
7th International Conference on Learning Representations, Iclr 2019
(January, 2019) [abs]
 Cheng, X; Mishne, G; Steinerberger, S, The geometry of nodal sets and outlier detection,
Journal of Number Theory, vol. 185
(April, 2018),
pp. 4864, Elsevier BV [doi]
 Yan, B; Sarkar, P; Cheng, X, Provable estimation of the number of blocks in block models,
International Conference on Artificial Intelligence and Statistics, Aistats 2018
(January, 2018),
pp. 11851194 [abs]
 Recent Grant Support
 NSFBSF: Group Invariant Graph Laplacians: Theory and Computations, National Science Foundation, 2020/072024/06.
 Efficient Methods for Calibration, Clustering, Visualization and Imputation of Large scRNAseq Data, Yale University, 2019/052023/01.
 HDR TRIPODS: Innovations in Data Science: Integrating Stochastic Modeling, Data Representation, and Algorithms, National Science Foundation, 2019/102022/09.
 Sloan Foundation Fellowship for Xiuyuan Cheng in Mathematics, Alfred P. Sloan Foundation, 2019/092021/09.
 CDS&E: Structureaware Representation Learning using Deep Networks, National Science Foundation, DMSNSF182082701, 2018/072021/06.
 Collaborative Research: Geometric Analysis and Computation of Generative Models, National Science Foundation, DMS1818945, 2018/072021/06.


dept@math.duke.edu
ph: 919.660.2800
fax: 919.660.2821
 
Mathematics Department
Duke University, Box 90320
Durham, NC 277080320

