周声龙

基本信息

研究兴趣

• 最优化理论、算法及其应用：包括稀疏低秩、阶跃优化、分布式优化，特别地，对人工智能、机器学习、科学计算等领域中的优化问题感兴趣
• 详见个人主页：https://shenglongzhou.github.io/

招生专业

• 运筹学与控制论博士、硕士
• 数学博士、硕士
• 欢迎对最优化理论与算法、人工智能、机器学习等领域感兴趣的学生申请

教育背景

• 2014-10 至 2018-12，博士，英国南安普顿大学，运筹学 
• 2011-09 至 2014-03，硕士，北京交通大学，运筹学与控制论 
• 2007-09 至 2011-06，学士，北京交通大学， 信息与计算科学 

工作经历

• 2023-03 至今，           北京交通大学，数学与统计学院，教授
• 2021-06 至 2023-03，伦敦帝国理工学院，工程学院，副研究员
• 2020-02 至 2021-02，英国南安普顿大学，数学学院，讲师
• 2017-10 至 2020-01，英国南安普顿大学，数学学院，副研究员

论文/期刊

部分发表第一作者文章 (全部发表文章可参考 Publications 或者 Google Scholar):

• Shenglong Zhou, Lili Pan, Naihua Xiu, and Geoffrey Ye Li, A 0/1 constrained optimization solving sample average approximation for chance constrained programming, Mathematics of Operations Research, 2024. RG, ArXiv, Code
• Shenglong Zhou and Geoffrey Ye Li, Federated learning via inexact ADMM, IEEE Transactions on Pattern Analysis and Machine Intelligence, 45, 9699-9708, 2023. RG, ArXiv, Code
• Shenglong Zhou and Geoffrey Ye Li, FedGiA: An efficient hybrid algorithm for federated learning, IEEE Transactions on Signal Processing, 71, 1493-1508, 2023. RG, ArXiv, Code
• Shenglong Zhou, Sparse SVM for sufficient data reduction, IEEE Transactions on Pattern Analysis and Machine Intelligence, 44, 5560-5571, 2022. RG, ArXiv, Code
• Shenglong Zhou, Gradient projection newton pursuit for sparsity constrained optimization,  Applied and Computational Harmonic Analysis, 61, 75-100, 2022. RG, ArXiv, Code
• Shenglong Zhou, Ziyan Luo, Naihua Xiu, and Geoffrey Ye Li, Computing one-bit compressive sensing via double-sparsity constrained optimization,  IEEE Transactions on Signal Processing, 70, 1593-1608, 2022. RG, ArXiv, Code
• Shenglong Zhou, Lili Pan, Naihua Xiu, and Houduo Qi, Quadratic convergence of smoothing Newton's method for 0/1 loss optimization, SIAM Journal on Optimization, 31, 3184-3211, 2021. RG, ArXiv, Code
• Shenglong Zhou, Lili Pan, Mu Li, and Meijuan Shang, Newton hard-thresholding pursuit for sparse LCP via a new merit function, SIAM Journal on Scientific Computing, 43, A772-A799, 2021. RG, ArXiv, Code
• Shenglong Zhou, Naihua Xiu, and Houduo Qi, Global and quadratic convergence of Newton hard-thresholding pursuit, Journal of Machine Learning Research, 22, 1-45, 2021. RG, ArXiv, Code
• Shenglong Zhou, Lili Pan, and Naihua Xiu, Newton method for L0-regularized, Numerical Algorithms, 88, 1541-1570, 2021. RG, ArXiv, Code
• Shenglong Zhou, Naihua Xiu, and Houduo Qi, Robust Euclidean embedding via EDM optimization, Mathematical Programming Computation, 12, 337-387, 2019. Code
• Shenglong Zhou, Naihua Xiu, and Houduo Qi, A fast matrix majorization-projection method for penalized stress minimization with box constraints, IEEE Transactions on Signal Processing, 66, 4331-4346, 2018. Code
• Shenglong Zhou, Naihua Xiu, Yingnan Wang, Lingchen Kong, and Houduo Qi, A Null-space-based weighted l1 minimization approach to compressed sensing, Information and Inference: A Journal of the IMA , 5, 76-102, 2016. RG, Code

部分发表其他文章 ( * 通讯作者):

• Jun Fan, Jie Sun, Ailin Yan, and Shenglong Zhou*, An oracle gradient regularized Newton method for quadratic measurements regression, Applied and Computational Harmonic Analysis, 78, 101775, 2025. RG, ArXiv
• Kaidi Xu, Shenglong Zhou*, and Geoffrey Ye Li, Federated reinforcement learning for resource allocation in V2X networks, IEEE Journal of Selected Topics in Signal Processing, 18，1210-1221, 2024. RG, ArXiv
• Huajun Wang, Yuanhai Shao, Shenglong Zhou, Ce Zhang, and Naihua Xiu, Support vector machine classifier via L0/1 soft-margin loss, IEEE Transactions on Pattern Analysis and Machine Intelligence, 44, 7253-7265, 2022. RG, ArXiv, Code

部分最新Online文章 ( * 通讯作者):

• Shuai Li, Shenglong Zhou*, and Ziyan Luo, Sparse quadratically constrained quadratic programming via semismooth Newton method, 2025. RG, ArXiv, Code
• Shenglong Zhou, Ouya Wang, Ziyan Luo, Yongxu Zhu, and Geoffrey Ye Li, Preconditioned inexact stochastic ADMM for deep models, 2025. RG, ArXiv
• Shan Sha, Shenglong Zhou*, Lingchen Kong, and Geoffrey Ye Li, Sparse decentralized federated learning, 2025. RG, ArXiv
• Ouya Wang, Shenglong Zhou*, and Geoffrey Ye Li, BADM: Batch ADMM for deep learning, 2024. RG, ArXiv
• Ouya Wang, Shenglong Zhou*, and Geoffrey Ye Li, New environment adaptation with few shots for OFDM receiver and mmWave beamforming, Revised by IEEE Transactions on Signal Processing, 2023. RG, ArXiv
• Shenglong Zhou, Xianchao Xiu, Yingnan Wang, and Dingtao Peng, Revisiting Lq (0<=q<1) norm regularized optimization, 2023. RG, ArXiv, Code

科研项目

• 2023-2028，主持，300万元，国家重点研发计划，海量数据分析中的阶跃稀疏优化理论与方法

• 2023-2026，主持，100万元，其他部市，机器学习中的0/1损失优化理论与二阶算法研究

• 2023-2026，主持，100万元，自然科学类人才基金项目， 联邦学习中的最优化算法理论与应用

获奖与荣誉

• 2023年，IEEE MLSP 杰出论文奖
• 2022年，入选国家级青年人才计划
• 2019年，新世界数学奖博士论文优胜奖

软件著作权

部分软件与程序包（全部软件与程序可参考 Software 或者 Github）

• 稀疏优化：CSpack、NHTP、SNSQP、GPNP、PSNP、NL0R、IIHT、MIRL1、HTPCP 

• 阶跃优化：NM01、GPSP、L01ADMM、SNSCO

• 矩阵优化：SQREDM、PREEEDM

• 双层规划：BiOpt Toolbox、BOLIBver2

• 联邦学习：FedADMM、FedGiA、FedEPM

社会兼职