Publications

Preprints

1. J. Feng, J. Chen, and K. Wei, Global convergence of natural policy gradient with Hessian-aided momentum variance reduction. Preprint, 2024.

2. H. Chen, J. Chen, and K. Wei, A zeroth-order variance-reduced method for decentralized stochastic non-convex optimizations. Preprint, 2023.

3. J. Liu, W. Li, and K. Wei, On the Convergence of Projected Policy Gradient for Any Constant Step Sizes. Preprint, 2023.

4. J. Liu, J. Chen, and K. Wei, On the linear convergence of policy gradient under Hadamard parameterization. Preprint, 2023.

5. J. Luo, D. Yang, and K. Wei, Improved complexity analysis of the Sinkhorn and Greenkhorn algorithms for optimal transport. Preprint, 2023.

6. J. Chen, J. Feng, W. Gao and K. Wei, Decentralized natural policy gradient with variance reduction for collaborative multi-agent reinforcement learning. Preprint, 2022.

7. J.-F. Cai, W. Huang, H. Wang and K. Wei, Tensor completion via tensor train based low-rank quotient geometry under a preconditioned metric. Preprint, 2022.

Book Chapters

1. J.-F. Cai and K. Wei, Exploiting the structure effectively and efficiently in low rank matrix recovery. Handbook of Numerical Analysis, 9 (2018), pp. 21-51.

Journal Publications

1. H. Wang, J. Chen and K. Wei, Implicit regularization and entrywise convergence of Riemannian optimization for low Tucker-rank tensor completion. Journal of Machine Learning Research, 24 (347) (2023) pp. 1–84.

2. W. Huang and K. Wei, An inexact Riemannian proximal gradient method. Computational Optimization and Applications, 85 (2023), pp. 1–32.

3. J.-F. Cai and K. Wei, Solving systems of phaseless equations via Riemannian optimization with optimal sampling complexity. Journal of Computational Mathematics (accepted), 2022.

4. J. Chen, W. Gao, S. Mao, and K. Wei, Vectorized Hankel Lift: A convex approach for blind super-resolution of point sources. IEEE Transactions on Information Theory, 68 (12) (2022), pp. 8280–8309.

5. H. Wang, J.-F. Cai, T. Wang and K. Wei, Fast Cadzow's algorithm and a gradient variant. Journal of Scientific Computing, 88 (2021): 41.

6. W. Huang and K. Wei, An Extension of fast iterative shrinkage-thresholding to Riemannian optimization for sparse principal component analysis. Numerical Linear Algebra with Applications, 29 (1) (2022): 2049.

7. W. Huang and K. Wei, Riemannian proximal gradient methods. Mathematical Programming, 194 (2022), pp. 371–413.

8. J.-F. Cai, J. K. Choi, J. Li and K. Wei, Image restoration: Structured low rank matrix framework for piecewise smooth functions and beyond, Applied and Computational Harmonic Analysis, 56 (2022), pp. 26–60.

9. J. Chen, W. Gao and K. Wei, Exact matrix completion based on low rank Hankel structure in the Fourier domain. Applied and Computational Harmonic Analysis, 55 (2021), pp. 149–184.

10. J.-F. Cai, J. K. Choi and K. Wei, Data driven tight frame for compressed sensing MRI reconstruction via off-the-grid regularization. SIAM Journal on Imaging Science, 13(3) (2020), pp. 1272–1301.

11. K. Wei, J.-F. Cai, T. F. Chan and S. Leung, Guarantees of Riemannian optimization for low rank matrix completion. Inverse Problem and Imaging, 14(2) (2020), pp. 233–265.

12. Z. Li, J.-F. Cai and K. Wei, Towards the optimal construction of a loss function without spurious local minima for solving quadratic equations. IEEE Transactions on Information Theory, 66(5) (2020), pp. 3242–3260.

13. H. Cai, J.-F. Cai, and K. Wei, Accelerated alternating projections for robust principal component analysis. Journal of Machine Learning Research, 20 (2019), pp. 1–33.

14. X. Li, Y. Li, S. Ling, T. Strohmer and K. Wei, When do birds of a feather flock together? k-Means, proximity, and conic programming. Mathematical Programming, 179 (2020), 295–341.

15. J.-F. Cai, T. Wang, and K. Wei, Spectral compressed sensing via projected gradient descent. SIAM Journal on Optimization, 28(3) (2018), pp. 2625–2653.

16. X. Li, S. Ling, T. Strohmer and K. Wei, Rapid, robust, and reliable blind deconvolution via nonconvex optimization. Applied and Computational Harmonic Analysis, 47(3) (2019), pp. 893–934.

17. K. Wei, K. Yin, X.-C. Tai and T. F. Chan, New region force for variational models in image segmentation and high dimensional data clustering. Annals of Mathematical Sciences and Applications, 3(1) (2018), pp. 255–286.

18. T. Strohmer and K. Wei, Painless breakups - Efficient demixing of low rank matrices. Journal of Fourier Analysis and Applications, 25(1) (2019), pp. 1–31.

19. K. Xu, A. P. Austin and K. Wei, A fast algorithm for the convolution of functions with compact support using Fourier extensions. SIAM Journal on Scientific Computing, 39(6) (2017), pp. A3089–A3106.

20. J.-F. Cai, T. Wang and K. Wei, Fast and provable algorithms for spectrally sparse signal reconstruction via low-rank Hankel matrix completion. Applied and Computational Harmonic Analysis, 46(1) (2019), pp. 94–121.

21. K. Wei, J.-F. Cai, T. F. Chan and S. Leung, Guarantees of Riemannian optimization for low rank matrix recovery. SIAM Journal on Matrix Analysis and Applications, 37(3) (2016), pp. 1198–1222.

22. K. Wei, Solving systems of phaseless equations via Kaczmarz methods: A proof of concept study. Inverse Problems, 31(12) (2015):125008.

23. J. Tanner and K. Wei, Low rank matrix completion by alternating steepest descent methods. Applied and Computational Harmonic Analysis, 40(2) (2016), pp. 417–429.

24. J. Blanchard, J. Tanner and K. Wei, CGIHT: Conjugate gradient iterative hard thresholding for compressed sensing and matrix completion. Information and Inference: A Journal of IMA, 4(4) (2015), pp. 289–327.

25. J. Blanchard, J. Tanner and K. Wei, Conjugate gradient iterative hard thresholding: Observed noise stability for compressed sensing. IEEE Transactions on Signal Processing, 63(2) (2015), pp. 528–537.

26. K. Wei, Fast iterative hard thresholding for compressed sensing. IEEE Signal Processing Letters, 22(5) (2015), pp. 593–597.

27. J. Tanner and K. Wei, Normalized iterative hard thresholding for matrix completion. SIAM Journal on Scientific Computing, 35(5) (2013), pp. S104–S125