张娇娇|助理教授

、

       jiaoz@gbu.edu.cn          

               2011-2015，哈尔滨工业大学，自动化，学士

       2015-2018，中国科学技术大学，自动化，硕士 

              2018-2022，香港中文大学，系统工程与工程管理，博士                                           

科研领域

---

      

    张娇娇，博士毕业于香港中文大学，现为大湾区大学（筹）智能计算中心助理教授。主要研究方向：最优化算法与理论及其在分布式优化、联邦学习、安全鲁棒计算与隐私保护等领域的应用。研究成果发表于 IEEE Trans on Signal Processing、IEEE Trans on Automatic Control、IEEE Trans on Signal and Information Processing over Networks 等国际权威期刊，以及NeurIPS、ICLR等机器学习领域的重要学术会议。其第一作者论文荣获国际信号处理领域旗舰会议 IEEE International Conference on Acoustics, Speech, and Signal Processing （ICASSP 2024）最佳论文奖。2018年获香港博士研究生奖学金计划（HKPFS），2022年获瑞典数字未来博士后奖学金计划（Digital Futures）。2024年入选国家级青年人才计划。

      个人简历：https://jiaojiaozhang-jjz.github.io//

工作经历

---

• 2022-2025，KTH-瑞典皇家理工学院电气工程与计算机科学系，博士后

主要成果

---

• Jiaojiao Zhang Huikang Liu, Anthony Man-Cho So and Qing Ling. “Variance-Reduced Stochastic

Quasi-Newton Methods for Decentralized Learning.” IEEE Transactions on Signal Processing (2023).

• Jiaojiao Zhang, Huikang Liu, Anthony Man-Cho So and Qing Ling. “A Penalty Alternating Direction

Method of Multipliers for Convex Composite Optimization over Decentralized Networks.” IEEE

Transactions on Signal Processing (2021).

• Jiaojiao Zhang, Qing Ling and Anthony Man-Cho So. “A Newton Tracking Algorithm with Exact

Linear Convergence for Decentralized Consensus Optimization.” IEEE Transactions on Signal and

Information Processing over Networks (2021).

• Jiaojiao Zhang, Shuang Cong, Qing Ling, Kezhi Li and Herschel Rabitz. “Quantum State Filter with

Disturbance and Noise.” IEEE Transactions on Automatic Control (2019).

• Jiaojiao Zhang, Shuang Cong, Qing Ling and Kezhi Li. “An Efficient and Fast Quantum State

Estimator with Sparse Disturbance.” IEEE Transactions on Cybernetics (2018).

• Jiaojiao Zhang, Kezhi Li and Shuang Cong. “Efficient Reconstruction of Density Matrices for High

Dimensional Quantum State Tomography.” Signal Processing (2017).

•  Huikang Liu, Jiaojiao Zhang*, Anthony Man-Cho So and Qing Ling. “A Communication-Efficient

Decentralized Newton’s Method with Provably Faster Convergence.” IEEE Transactions on Signal and Information Processing over Networks (2023). (I am the corresponding author)