曾锦山，西安交通大学数学专业博士。现为西安交通大学管理学院市场营销系教授（青拔A类），博士生导师。目前主要研究兴趣包括人工智能中的优化算法理论、联邦学习、大语言模型及其在管理科学中的应用。入选江西省重大人才计划，主持国家自然科学基金3项和江西省自然科学基金杰出青年项目。已在国际主流期刊或会议上发表高水平论文80余篇，授权发明专利20余项，荣获2025国际基础科学大会“前沿科学奖”、2018和2020“世界华人数学家联盟最佳论文奖”。受邀在2025国际基础科学大会上作前沿科学奖报告，在数届世界华人数学家大会上作学术报告。受邀担任国际高水平学术会议副主席或论坛主席10余次，指导学生获得“挑战杯”国家特等奖等国家级学科竞赛奖励30余项。

2015.07-2018.12  江西师范大学计算机信息工程学院  讲师

2017.04-2018.03  香港科技大学数学系 访问学者

2018.08-2019.02  香港科技大学数学系 访问学者

2019.01-2023.12  江西师范大学计算机信息工程学院  副教授

2019.09-2020.09  香港城市大学数据科学学院 访问学者

2022.06-2025.05  江西师范大学计算机信息工程学院  副院长

2024.01-2025.06  江西师范大学计算机信息工程学院  教授

2025.07-至今   西安交通大学管理学院  教授

2004.09-2008.07  西安交通大学 信息与计算科学 学士学位

2008.09-2015.06  西安交通大学 数学 博士学位（硕博连读）

2013.11-2014.11  加州大学洛杉矶分校 数学 联合培养博士

人工智能与管理科学交叉研究

[1] Jinshan Zeng, Yiyang Yuan, Yan Zhang, Xijia Wang, Yefei Wang, Cross-lingual font generation via patch-level style contrastive learning and relative position awareness, Pattern Recognition, 169: 1-14, 111937, 2026.

[2] Yong Chen, Feiwang Yuan, Wenzhen Lai, Jinshan Zeng, Wei He, Qing Huang, Low-rank tensor meets deep prior: Coupling model-driven and data-driven methods for hyperspectral image reconstruction, IEEE Transactions on Circuits and Systems for Video Technology, 2025, doi:10.1109/TCSVT.2025.3575470

[3] Shengkun Zhu, Feiteng Nie, Jinshan Zeng, Sheng Wang, Yuan Sun, Yuan Yao, Shangfeng Chen, Quanqing Xu, Chuanhui Yang, FedAPM: Federated learning via ADMM with partial model personalization, KDD ’25, August 3–August 7, 2025, Toronto, Canada.

[4] Jinshan Zeng, Xianglong Yu, Xianchao Tong, Wenyan Xiao, Self-supervised collaborative information bottleneck for text readability assessment, Association for the Advancement of Artificial Intelligence (AAAI), Philadelphia, USA, 25 February - 04 March, 2025.

[5] Ke Ma, Qianqian Xu, Jinshan Zeng, Wei Liu, Xiaochun Cao, Yingfei Sun, and Qingming Huang, Sequential manipulation against rank aggregation: Theory and algorithm, IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(12): 9353 - 9370, 2024.

[6] Yong Chen, Wenzhen Lai, Wei He, Xi-Le Zhao, Jinshan Zeng, Hyperspectral compressive snapshot reconstruction via coupled low-rank subspace representation and self-supervised deep network, IEEE Transactions on Image Processing, Jan. 2024, vol. 33, pages:926-941.

[7]Yong Chen, Maolin Chen, Wei He, Jinshan Zeng, Min Huang, Yubang Zheng, Thick cloud removal in multitemporal remote sensing images via low-rank regularized self-supervised network, IEEE Transactions on Geoscience and Remote Sensing, vol. 62, pages: 1-13, February 10, 2024.

[8]Jinshan Zeng, Xianchao Tong, Xianglong Yu, Wenyan Xiao, Qing Huang, InterpretARA: Enhancing hybrid automatic readability assessment with linguistic feature interpreter and contrastive learning, Association for the Advancement of Artificial Intelligence (AAAI), vol 38(17): 19497-19505, Vancouver, Canada, 22-25 February, 2024.

[9] Yong Chen, Xinfeng Gui, Jinshan Zeng, Xi-Le Zhao, Wei He, Combining low-rank and deep plug-and-play priors for snapshot compressive imaging, IEEE Transactions on Neural Networks and Learning Systems, 35(11): 16396-16408, Nov. 1, 2024.

[10] Yanwei Fu, Chen Liu, Donghao Li, Zuyuan Zhong, Xinwei Sun, Jinshan Zeng, Yuan Yao, Exploring structural sparsity of deep networks via inverse scale spaces, IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(2):1749-1765, February 01, 2023.

[11] Ke Ma, Qianqian Xu, Jinshan Zeng,  Guorong Li,  Xiaochun Cao, Qingming Huang, A tale of HodgeRank and spectral method: Target attack against rank aggregation is the fixed point of adversarial game, IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(4): 4090-4108, April 2023.

[12] Ke Ma, Qianqian Xu, Jinshan Zeng, Xiaochun Cao, Qingming Huang, Poisoning attack against estimating from pairwise comparisons, IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(10): 6393 - 6408, October 01, 2022.

[13] Yong Chen, Wei He, Xi-Le Zhao, Ting-Zhu Huang, Jinshan Zeng, and Hui Lin, Exploring nonlocal group sparsity under transform learning for hyperspectral image denoising, IEEE Transactions on Geoscience and Remote Sensing, Vol. 60, 2022, Article No. 5537518.

[14] Jinshan Zeng, Wotao Yin, Ding-Xuan Zhou, Moreau envelope augmented Lagrangian method for nonconvex optimization with linear constraints, Journal of Scientific Computing, 91:61,2022.

[15] Jinshan Zeng, Min Zhang, Shao-Bo Lin, Fully corrective gradient boosting with squared hinge: Fast learning rates and early stopping, Neural Networks, 147:136-151,2022.

[16] Yong Chen, Jinshan Zeng, Wei He, Xi-Le Zhao, and Ting-Zhu Huang, Hyperspectral and multispectral image fusion using factor smoothed tensor ring decomposition, IEEE Transactions on Geoscience and Remote Sensing, 60:1-17, 2022.

[17] Jinshan Zeng, Shao-Bo Lin, Yuan Yao, Ding-Xuan Zhou, On ADMM in deep learning: Convergence and saturation-avoidance, Journal of Machine Learning Research, 22 (199):1-67, Sep. 2021.

[18] Jinshan Zeng, Qi Chen, Yunxin Liu, Mingwen Wang and Yuan Yao, StrokeGAN: Reducing mode collapse in Chinese font generation via stroke encoding, in the Thirty-Fifth Association for the Advancement of Artificial Intelligence (AAAI-21), 35(4): 3270-3277, February 2-9, 2021, page: 3270-3277.

[19] Yanwei Fu, Chen Liu, Donghao Li, Xinwei Sun, Jinshan Zeng, and Yuan Yao, DessiLBI: Exploring Structural Sparsity of Deep Networks via Differential Inclusion Paths, in Proceedings of the 37th International Conference on Machine Learning (ICML), July 12-18, 2020.

[20] Yu Wang, Wotao Yin, and Jinshan Zeng, Global convergence of ADMM in nonconvex nonsmooth optimization, Journal of Scientific Computing, 78(1):29-63, 06 January, 2019.

[21] Jinshan Zeng, Ke Ma, and Yuan Yao, On global linear convergence in stochastic nonconvex optimization for semidefinite programming, IEEE Transactions on Signal Processing, 67(16): 4261-4275, Aug. 2019.

[22] Jinshan Zeng, Tim Tsz-Kit Lau, Shao-Bo Lin, and Yuan Yao, Global convergence of block coordinate descent in deep learning, in Proceedings of the 36th International Conference on Machine Learning (ICML), Long Beach, California, PMLR 97: 7313-7323, June 9-15, 2019.

[23] Shaobo Lin, and Jinshan Zeng. Fast learning with polynomial kernel. IEEE Transactions on Cybernetics, 49(10): 3780-3792, October 2019.

[24] Shaobo Lin, Jinshan Zeng, and Xiaoqin Zhang, Constructive neural network learning, IEEE Transactions on Cybernetics, 49(1): 221-232, January 2019.

[25] Jinshan Zeng, and Wotao Yin. On nonconvex decentralized gradient descent. IEEE Transactions on Signal Processing. 66(11): 2834-2848, 01 June, 2018.

[26] Jinshan Zeng, Shaobo Lin, and Zongben Xu, Sparse regularization: Convergence of iterative jumping thresholding algorithm, IEEE Transactions on Signal Processing, 64(19): 5106-5117, Oct. 2016.

[27] Yu Wang, Jinshan Zeng, Zhimin Peng, Xiangyu Chang, and Zongben Xu, Linear convergence of adaptively iterative thresholding algorithms for compressed sensing, IEEE Transactions on Signal Processing, 63(11): 2957-2971, June 1, 2015.

[28] Jinshan Zeng, Shaobo Lin, Yao Wang, and Zongben Xu. L1/2 regularization: convergence of iterative Half thresholding algorithm. IEEE Transactions on Signal Processing, 62(9): 2317-2329, May 1, 2014.

[1] 2024年01月-2027年12月，高效公平的个性化联邦学习算法与理论，国家自然科学基金面上项目，62376110，在研，主持

[2] 2023年01月-2025年12月，新型深度学习算法理论及其在轻量级神经网络训练中的应用，江西省自然科学基金杰出青年项目，20224ACB212004，在研，主持

[3] 2020年01月-2024年12月，基于Gradient-free的深度学习算法设计及收敛性分析，江西省重大人才计划，jxsq2019201124，已结题，主持

[4] 2020年01月-2023年12月，深度神经网络训练算法的收敛性与泛化性研究，国家自然科学基金面上项目，61977038，已结题，主持

[5] 2017年01月-2019年12月，有向图上的去中心式一致优化算法及收敛性研究，国家自然科学基金青年项目，61603162，已结题，主持

[1] 2025国际基础科学大会前沿科学奖报告，报告名称：Global convergence of ADMM in nonconvex nonsmooth optimization，2025年7月14日，北京

[2] 2020世界华人数学家大会最佳论文奖报告，报告名称：On ADMM in deep learning: Convergence and saturation- avoidance，2020年12月28日，合肥

[3] 2018世界华人数学家大会最佳论文奖报告，报告名称：Linear convergence of adaptively iterative thresholding algorithms for compressed sensing，2018年12月28日，台北