Ganzhao Yuan

Associate Professor
Shenzhen University of Advanced Technology (SUAT), China

Email: yuanganzhao[at]foxmail[dot]com
Short Biography

My name is Ganzhao Yuan. I earned my Ph.D. from the School of Computer Science and Engineering at South China University of Technology. Previously, I served as a Postdoctoral Researcher at the School of Mathematics at South China University of Technology and at the Visual Computing Center at King Abdullah University of Science and Technology (KAUST). I also worked as an Associate Researcher at Sun Yat-sen University and Peng Cheng Laboratory.

Currently, I am an Associate Professor at the Shenzhen University of Advanced Technology (SUAT). My research interests center on mathematical optimization—including stochastic, nonsmooth, and nonconvex optimization—and its applications in machine learning, large language models, and generative AI.

I am actively recruiting self-motivated Ph.D. students and postdoctoral researchers to join my team at SUAT. Please feel free to email me if you are interested.

Selected Publications
  1. Da Chang, Ganzhao Yuan. MGUP: A Momentum-Gradient Alignment Update Policy for Stochastic Optimization. Annual Conference on Neural Information Processing Systems (NeurIPS), 2025. [Spotlight, Acc. Rate=688/21575=3%]
    [Paper][Code][Poster]

  2. Ganzhao Yuan. ADMM for Nonconvex Optimization under Minimal Continuity Assumption. International Conference on Learning Representations (ICLR), 2025.
    [Paper][Code][Poster]

  3. Ganzhao Yuan. ADMM for Structured Fractional Minimization. International Conference on Learning Representations (ICLR), 2025.
    [Paper][Code][Poster]

  4. Ganzhao Yuan. Smoothing Proximal Gradient Methods for Nonsmooth Sparsity Constrained Optimization: Optimality Conditions and Global Convergence. International Conference on Machine Learning (ICML), 2024.
    [Paper][Code][Poster]

  5. Ganzhao Yuan. Coordinate Descent Methods for Fractional Minimization. International Conference on Machine Learning (ICML), 2023. [CCF A]
    [Paper][Code][Slide]

  6. Ganzhao Yuan. Coordinate Descent Methods for DC Minimization: Optimality Conditions and Global Convergence. Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2023. [CCF A]
    [Paper][Code][Slide][Poster]

  7. Ganzhao Yuan, Li Shen, Wei-Shi Zheng. A Block Decomposition Algorithm for Sparse Optimization. ACM International Conference on Knowledge Discovery and Data Mining (SIGKDD), 2020. [CCF A]
    [Paper][Code][Slide]

  8. Ganzhao Yuan, Li Shen, Wei-Shi Zheng. A Decomposition Algorithm for the Sparse Generalized Eigenvalue Problem. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019. [CCF A]
    [Paper][Code][Slide]

  9. Qing Zhang, Ganzhao Yuan, Chunxia Xiao, Lei Zhu, Wei-Shi Zheng. High-Quality Exposure Correction of Underexposed Photos. ACM Multimedia, 2018. [CCF A]
    [Paper]

  10. Ganzhao Yuan, Bernard Ghanem. L0TV: A Sparse Optimization Method for Impulse Noise Image Restoration. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2018. [CCF A]
    [Paper][Code]

  11. Li Shen, Wei Liu, Ganzhao Yuan, Shiqian Ma. GSOS: Gauss-Seidel Operator Splitting Algorithm for Multi-Term Nonsmooth Convex Composite Optimization. International Conference on Machine Learning (ICML), 2017. [CCF A]
    [Paper]

  12. Ganzhao Yuan, Wei-Shi Zheng, Bernard Ghanem. A Matrix Splitting Method for Composite Function Minimization. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017. [CCF A]
    [Paper][Code][Slide]

  13. Ganzhao Yuan, Bernard Ghanem. An Exact Penalty Method for Binary Optimization Based on MPEC Formulation.Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), pp. 2867-2875, 2017. [CCF A]
    [Paper][Code]

  14. Ganzhao Yuan, Yin Yang, Zhenjie Zhang, Zhifeng Hao. Convex Optimization for Linear Query Processing under Approximate Differential Privacy. ACM International Conference on Knowledge Discovery and Data Mining (SIGKDD), pp. 2005-2014, 2016. [CCF A]
    [Paper] [Code]

  15. Ganzhao Yuan, Bernard Ghanem. A Proximal Alternating Direction Method for Semidefinite Rank Minimization.Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), pp. 2300-2308, 2016. [CCF A]
    [Paper][Code]

  16. Ganzhao Yuan, Zhenjie Zhang, Marianne Winslett, Xiaokui Xiao, Yin Yang, Zhifeng Hao.Optimizing Batch Linear Queries under Exact and Approximate Differential Privacy. ACM Transactions on Database Systems (TODS), 40(2): 11:1-11:47, 2015. [CCF A]
    [Paper][Code]

  17. Ganzhao Yuan, Bernard Ghanem. L0TV: A New Method for Image Restoration in the Presence of Impulse Noise. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5369-5377, 2015. [Oral, Acc. Rate=71/2151=3.3%, CCF A]
    [Paper][Code][Slide][Abstract]

  18. Ganzhao Yuan, Zhenjie Zhang, Marianne Winslett, Xiaokui Xiao, Yin Yang, Zhifeng Hao. Low-Rank Mechanism: Optimizing Batch Queries under Differential Privacy. International Conference on Very Large Data Bases (VLDB), 5(11):1352-1363, 2012. [CCF A]
    [Paper][Code][Slide]

  19. Ganzhao Yuan, Zhenjie Zhang, Bernard Ghanem, Zhifeng Hao. Low-Rank Quadratic Semidefinite Programming. Neurocomputing, 106(0):51-60, 2013.
    [Paper][Code]

  20. Zhifeng Hao, Ganzhao Yuan, Xiaowei Yang, Zijie Chen. A Primal Method for Multiple Kernel Learning. Neural Computing and Applications 23(3-4):975-987, 2013.
    [Paper][Code]

  21. Zhifeng Hao, Ganzhao Yuan, Bernard Ghanem. BILGO: Bilateral Greedy Optimization for Large Scale Semidefinite Programming. Neurocomputing, 127(0):247-257, 2014.
    [Paper][Code]

Recent Preprints
  1. Da Chang, Yongxiang Liu, Ganzhao Yuan. On the Convergence of Muon and Beyond. arXiv preprint, Sep 2025.
    [Paper]

  2. Ganzhao Yuan. Adaptive Extrapolated Proximal Gradient Methods with Variance Reduction for Composite Nonconvex Finite-Sum Minimization. arXiv preprint, Feb 2025.
    [Paper]

  3. Ganzhao Yuan. ADMM for Nonsmooth Composite Optimization under Orthogonality Constraints. arXiv preprint, May 2024.
    [Paper]

  4. Ganzhao Yuan. A Block Coordinate Descent Method for Nonsmooth Composite Optimization under Orthogonality Constraints. arXiv preprint, 2023.
    [Paper][Slide]

  5. Di He, Ganzhao Yuan, Xiao Wang, Pengxiang Xu. Block Coordinate Descent Methods for Optimization under J-Orthogonality Constraints with Applications. arXiv preprint, June 2024.
    [Paper]

Unpublished Papers
  1. Ganzhao Yuan, Bernard Ghanem. Sparsity Constrained Minimization via Mathematical Programming with Equilibrium Constraints. arXiv preprint, 2016.
    [Paper]

  2. Ganzhao Yuan, Bernard Ghanem. Binary Optimization via Mathematical Programming with Equilibrium Constraints. arXiv preprint, 2016.
    [Paper]

  3. Ganzhao Yuan, Li Shen, Wei-Shi Zheng. A Hybrid Method of Combinatorial Search and Coordinate Descent for Discrete Optimization. arXiv preprint, 2017.
    [Paper]