Sections
Left Column
Image
Image
jfcai
Image Caption

CAI, Jian-Feng
蔡劍鋒

(PhD Chinese Univ of Hong Kong)

Phone: (852) 3469 2248
Email: jfcai@ust.hk
Office: Room 3436
Home Page
Right Column
Image
Image

Professor



Research Interests

Theoretical and algorithmic foundations of problems related to information, data, and signals, with applications to inverse problems, signal processing, and machine learning.

Teaching

  • MATH3322  Matrix Computation
  • MATH5312  Advanced Numerical Methods II
  • MATH6914W  Reading Course: Mathematical Foundations of Data Science III

Selected Publications

  Article

  1. Improved Harmonic Incompatibility Removal for Susceptibility Mapping via Reduction of Basis Mismatch
    • Author(s): Bao, Chenglong; Cai, Jianfeng; Choi, Jae Kyu; Dong, Bin; Wei, Ke
    • Source: Journal of Computational Mathematics, v. 40, (6), 2022, p. 914-937
    • Year: 2022

  2. Sample-Efficient Sparse Phase Retrieval via Stochastic Alternating Minimization
    • Author(s): Cai, Jianfeng; Jiao, Yuling; Lu, Xiliang; You, Juntao
    • Source: IEEE Transactions on Signal Processing, v. 70, 12 October 2022, article number 9917336, p. 4951-4966
    • Year: 2022

  3. Generalized Low-rank plus Sparse Tensor Estimation by Fast Riemannian Optimization
    • Author(s): Cai, Jian-Feng; Li, Jingyang; Xia, Dong
    • Source: Journal of the American Statistical Association, April 2022
    • Year: 2022

  4. Solving phase retrieval with random initial guess is nearly as good as by spectral initialization
    • Author(s): Cai, Jianfeng; Huang, Meng; Li, Dong; Wang, Yang
    • Source: Applied and Computational Harmonic Analysis, v. 58, May 2022, p. 60-84
    • Year: 2022

  5. The Global Landscape of Phase Retrieval II: Quotient Intensity Models
    • Author(s): Cai, Jianfeng; Huang, Meng; Li, Dong; Wang, Yang
    • Source: Annals of Applied Mathematics, v. 38, (1), January 2022, p. 62-114
    • Year: 2022

  6. Provable Tensor-Train Format Tensor Completion by Riemannian Optimization
    • Author(s): Cai, Jianfeng; Li, Jingyang; Xia, Dong
    • Source: Journal of Machine Learning Research, v. 23, 2022, p. 1-77
    • Year: 2022

  7. Image Restoration: Structured Low Rank Matrix Framework For Piecewise Smooth Functions And Beyond
    • Author(s): Cai, Jianfeng; Choi, Jae Kyu; Li, Jingyang; Wei, ke
    • Source: Applied and Computational Harmonic Analysis, v. 56, January 2022, p. 26-60
    • Year: 2022

  8. Enhanced Expressive Power and Fast Training of Neural Networks by Random Projections
    • Author(s): Cai, Jianfeng; Li, Dong; Sun, Jiaze; Wang, Ke
    • Source: CSIAM Transactions on Applied Mathematics, v. 2, (3), August 2021, p. 532-550
    • Year: 2021

  9. The Global Landscape of Phase Retrieval I: Perturbed Amplitude Models
    • Author(s): Cai, Jianfeng; Huang, Meng; Li, Dong; Wang, Yang
    • Source: Annals of Applied Mathematics, v. 37, (4), December 2021, p. 437-512
    • Year: 2021

  10. Accelerated Structured Alternating Projections for Robust Spectrally Sparse Signal Recovery
    • Author(s): Cai, Hanqin; Cai, Jianfeng; Wang, Tianming; Yin, Guojian
    • Source: IEEE Transactions on Signal Processing, v. 69, 6 January 2021, article number 9316310, p. 809-821
    • Year: 2021

  11. Towards the optimal construction of a loss function without spurious local minima for solving quadratic equations
    • Author(s): Li, Zhenzhen ; Cai, Jianfeng; Wei, Ke
    • Source: IEEE Transactions on Information Theory, v. 66, (5), May 2020, article number 8918236, p. 3242-3260
    • Year: 2020

  12. Guarantees of riemannian optimization for low rank matrix completion
    • Author(s): Wei, Ke; Cai, Jianfeng; Chan, Tony Fan-cheong; Leung, Shing Yu
    • Source: Inverse Problems and Imaging, v. 14, (2), April 2020, p. 233-265
    • Year: 2020

  13. Accelerated Alternating Projections for Robust Principal Component Analysis
    • Author(s): Cai, HanQin; Cai, Jian-Feng ; Wei, Ke
    • Source: Journal of Machine Learning Research, v. 20, 2019
    • Year: 2019

  14. Fast and Provable Algorithms for Spectrally Sparse Signal Reconstruction via Low-rank Hankel Matrix Completion
    • Author(s): Cai, Jianfeng ; Wang, Tianming; Wei, Ke
    • Source: Applied and Computational Harmonic Analysis, v. 46, (1), January 2019, p. 94-121
    • Year: 2019

  15. Data-driven tight frame construction and image denoising
    • Author(s): Cai, Jianfeng; Ji, Hui; Shen, Zuowei; Ye, Guibo
    • Source: Applied and Computational Harmonic Analysis. , v. 37, (1), 2014, p. 89-105
    • Year: 2014

  16. Image Restoration: Total Variation; Wavelet Frames; and Beyond
    • Author(s): Cai, Jianfeng; Dong, Bin; Osher, Stanley; Shen, Zuowei
    • Source: Journal of the American Mathematical Society. , v. 25, (4), 2012, p. 1033-1089
    • Year: 2012

  17. A singular value thresholding algorithm for matrix completion
    • Author(s): Cai, Jian-Feng; Candès, Emmanuel J.; Shen, Zuowei
    • Source: SIAM J. Optimiz.. , v. 20, (4), p. 1956-1982
    • Year: 2010

  18. Split Bregman Methods and Frame Based Image Restoration
    • Author(s): Cai, Jian-Feng; Osher, Stanley; Shen, Zuowei
    • Source: Multiscale Modeling and Simulation. , v. 8, Issue 2, 2009, p. 337-369
    • Year: 2009