我目前在西安电子科技大学人工智能学院攻读博士学位👨‍🎓。 我的研究兴趣主要包括😎😎😎: ✔️ 优化和泛化 (Optimization and Generalization) 优化、泛化方法与理论 (Methods and Theory) 联邦学习 (Federated Learning) 差分隐私 (Differential Privacy) ✔️ 模型可解释性 (Model Interpretability) 学习优化 (Learning to Optimize) 🔜 可信人工智能 (Trustworthy Artificail Intelligence)

📧 [E-mail] 🎓 [Google Scholar] 📥 [GitHub] 📑 [English Page]

教育经历

• 2024.10 ~ 现在: 新加坡南洋理工大学, 计算与数据科学学院, 访问博士 (CSC) [导师: 💁‍♂️Han Yu教授👍]

• 2020.09 ~ 现在: 西安电子科技大学, 人工智能学院, 在读博士 [导师: 💁‍♂️刘园园教授👍]

• 2016.09 ~ 2020.07: 西安理工大学, 理学院, 学士

学术论文

期刊论文

• DEs-Inspired Accelerated Unfolded Linearized ADMM Networks for Inverse Problems
  Weixin An, Yuanyuan Liu, Fanhua Shang, Hongying Liu, and Licheng Jiao
  IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2024.
  [SCI 1区期刊] 相关下载链接: [PDF][Code][Supplementary Material]

• Laplacian smoothing stochastic ADMMs with differential privacy guarantees
  Yuanyuan Liu, Jiacheng Geng, Fanhua Shang, Weixin An, Hongying Liu, and Qi Zhu
  IEEE Transactions on Information Forensics and Security (TIFS), 2022.
  [SCI 1区期刊] 相关下载链接: [PDF]

• Loopless Variance Reduced Stochastic ADMM for Equality Constrained Problems in IoT Applications
  Yuanyuan Liu, Jiacheng Geng, Fanhua Shang, Weixin An, Hongying Liu, and Qi Zhu
  IEEE Internet of Things Journal (IOT), 2021.
  [SCI 1区期刊] 相关下载链接: [PDF]

• Stochastic Variance Reduced Primal–Dual Hybrid Gradient Methods for Saddle-Point Problems
  Weixin An, Yuanyuan Liu, Fanhua Shang, and Hongying Liu
  Mathematics, 2025.
  [SCI 3区期刊]

会议论文

• Tight High-Probability Bounds for Nonconvex Heavy-Tailed Scenario under Weaker Assumptions
  Weixin An, Yuanyuan Liu, Fanhua Shang, Han Yu, Junkang Liu, and Hongying Liu
  Advances in Neural Information Processing Systems (NeurIPS'25), 2025.
  [CCF A类会议] 相关下载链接: [PDF]

• Robust and Faster Zeroth-Order Minimax Optimization: Complexity and Applications
  Weixin An, Yuanyuan Liu, Fanhua Shang, and Hongying Liu
  Advances in Neural Information Processing Systems (NeurIPS'24), 2024.
  [CCF A类会议] 相关下载链接: [PDF][Code][Supplementary Material]

• A Single-loop Accelerated Extra-gradient Difference Algorithm with Improved Complexity Bounds for Constrained Minimax Optimization
  Yuanyuan Liu, Fanhua Shang, Weixin An, Junhao Liu, Hongying Liu, and Zhouchen Lin
  Advances in Neural Information Processing Systems (NeurIPS'23), 2023.
  [CCF A类会议] 相关下载链接: [PDF][Code]

• A Numerical DEs Perspective on Unfolded Linearized ADMM Networks for Inverse Problems
  Weixin An, Yingjie Yue, Yuanyuan Liu, Fanhua Shang, and Hongying Liu
  Proceedings of the 30th ACM International Conference on Multimedia (ACM MM'22), 2022.
  [CCF A类会议] 相关下载链接: [PDF]

• Kill a Bird with Two Stones: Closing the Convergence Gaps in Non-Strongly Convex Optimization by Directly Accelerated SVRG with Double Compensation and Snapshots
  Yuanyuan Liu, Fanhua Shang, Weixin An , Hongying Liu, and Zhouchen Lin
  International Conference on Machine Learning (ICML'22), 2022.
  [CCF A类会议] 相关下载链接: [PDF]

荣誉奖励

• 博士研究生国家奖学金 (2024.10)

• 2024年度国家留学基金委公派留学奖学金 (2024.08)

• 2024西安电子科技大学优秀博士学位论文资助基金 (2024.03)

• 博士研究生国家奖学金 (2022.10)

• 西安理工大学优秀毕业生称号 (2021.05)

课题项目

• 国家自然科学基金重点项目(No. 2022ZD0160302), 2022-2026
  项目参与者
  深度学习网络设计与优化算法
  

• 国家自然科学基金面上项目(No. 61976164), 2019-2023
  项目骨干; 经费:61万元
  多元图卷积网络及其在极化SAR异质地物分类中的研究
  

• 国家自然科学基金面上项目 (No. 61876221), 2018-2022
  项目骨干; 经费:62万元
  大规模机器学习的动量加速方法的理论研究与应用
  

• 国家自然科学基金面上项目 (No. 61876220), 2018-2022
  项目骨干; 经费:62万元
  加速的随机方差减少优化方法及理论研究
  

学术服务

期刊审稿

• IEEE Transactions on Instrumentation & Measurement, TIM 2024

• IEEE Transactions on Neural Networks and Learning Systems, TNNLS 2024

会议审稿

• Annual Conference on Neural Information Processing Systems, NeurIPS 2023, 2025审稿人

• International Conference on Multimedia, ACM MM 2024, 审稿人

• The Thirteenth International Conference on Learning Representations, ICLR 2025, 审稿人

• International Joint Conference on Artificial Intelligence (IJCAI'24), PC Member

• International Workshop on Federated Learning with Generative AI In Conjunction with IJCAI 2025, PC Member

网站访问统计 (自2025年2月起)