Scholar
Jian-Feng Cai
Google Scholar ID: Mo4v5iwAAAAJ
Professor of Mathematics, Hong Kong University of Science and Technology
Citations & Impact
Citations
6,518
H-index
35
i10-index
70
Publications
20
Co-authors
61
list available
Publications
Resume (English only)
Academic Achievements
- Finding Low-Rank Matrix Weights in DNNs via Riemannian Optimization: RAdaGrad and RAadmW, NeurIPS 2025
- Online Tensor Learning: Computational and Statistical Trade-offs, Adaptivity and Optimal Regret, Annals of Statistics
- Interlacing Polynomial Method for Matrix Approximation via Generalized Column and Row Selection, Foundations of Computational Mathematics
- Fast Non-convex Matrix Sensing with Optimal Sample Complexity, UAI 2025
- Preconditioned Riemannian Gradient Descent Algorithm for Low-Multilinear-Rank Tensor Completion, ICML 2025
- Fast and Provable Algorithms for Sparse PCA with Improved Sample Complexity, ICML 2025
- Computationally Efficient and Statistically Optimal Robust High-Dimensional Linear Regression, Annals of Statistics
- Flash Proton Radiation Therapy via a Stochastic Three-Operator Splitting Method, Inverse Problems
- Approximation Theory of Wavelet Frame Based Image Restoration, Applied and Computational Harmonic Analysis
- A Preconditioned Fast Iterative Hard Thresholding Algorithm for Spectrally Sparse Signal Reconstruction, 2024 IEEE 13rd SAM
Research Experience
- 2019--Present: Professor, Department of Mathematics, Hong Kong University of Science and Technology
- 2015--2019: Associate Professor, Department of Mathematics, Hong Kong University of Science and Technology
- 2011--2015: Assistant Professor, Department of Mathematics, University of Iowa
- 2009--2011: CAM Assistant Adjunct Professor, Department of Mathematics, University of California, Los Angeles
- 2007--2009: Research Scientist, Temasek Laboratories, National University of Singapore
Background
- Research interests include the theoretical and algorithmic foundations of problems related to information, data, and signals. Previous research focuses mainly on the efficient representation, sensing, and analysis of high-dimensional data, with applications to medical imaging, compressed sensing, signal processing, and machine learning.
