Xiaodong Li, Ph.D.

Research Interests

• High-Dimensional Statistics
• Network Analysis
• Machine Learning Theory
• Mathematical Signal Processing

Recent Publications

• Convex Relaxation Methods for Community Detection [PDF] Xiaodong Li, Yudong Chen, and Jiaming Xu, submitted.
• Subspace Perspective on Canonical Correlation Analysis: Dimension Reduction and Minimax Rates [PDF] Zhuang Ma and Xiaodong Li, submitted.
• Memory-efficient Kernel PCA via Partial Matrix Sampling and Nonconvex Optimization: a Model-free Analysis of Local Minima [PDF] Ji Chen and Xiaodong Li, submitted.
• Rapid, Robust, and Reliable Blind Deconvolution via Nonconvex Optimization [PDF] Xiaodong Li, Shuyang Ling, Thomas Strohmer, and Ke Wei, Applied and Computational Harmonic Analysis, to appear.
• Optimal Rates of Convergence for Noisy Sparse Phase Retrieval via Thresholded Wirtinger Flow [PDF] T. Tony Cai, Xiaodong Li (corresponding author), and Zongming Ma, the Annals of Statistics 44(5), 2221-2251, 2016.
• Dense error correction for low-rank matrices via principal component pursuit [PDF] A. Ganesh, J. Wright, X. Li, E. Candes and Y. Ma, Information Theory Proceedings (ISIT), 2010 IEEE International Symposium on, 1513-1517.

Education

• Stanford University, Ph.D