黄飞虎，南京航空航天大学 计算机科学与技术学院/人工智能学院/软件学院 教授，其于2017年12月在南京航空航天大学获得工学博士学位, 2018年9月至2022年7月在美国匹兹堡大学（University of Pittsburgh）任博士后研究员。2022年入选国家级青年人才计划。近年主要研究机器学习、高效优化、分布式学习、模型压缩(大模型轻量化)、大模型高效推理,已有30多篇论文发表在人工智能与机器学习国际重要期刊与会议，包括JMLR、TPAMI、ICML、NeurIPS、ICLR、AAAI、IJCAI、AISTATS、CVPR、ICCV、ECCV等。其担任人工智能、机器学习、数据挖掘与计算机视觉国际重要会议的30多次（高级）程序委员：ICML、NeurIPS、AAAI 、IJCAI 、KDD 、CVPR、ICCV、ICLR、AISTATS 等，也担任国际重要期刊JMLR、IEEE TPAMI、ML、IEEE TIP、SIAM Journal on Optimization等的审稿人。目前主持两项国家自然科学基金项目。个人相关论文见：https://scholar.google.com/citations?user=tRQwlHUAAAAJ&hl=en

机器学习与高效优化代表性论文：

[1] Feihu Huang, Shangqian Gao, Jian Pei and Heng Huang, Nonconvex Zeroth-Order Stochastic ADMM Methods with Lower Function Query Complexity, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2023. (CCF A类)  (已接收)

[2] Feihu Huang and Shangqian Gao. "Gradient Descent Ascent for Minimax Problems on Riemannian Manifolds." IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 45(7): 8466 – 8476, 2023. (CCF A类)

[3] Feihu Huang, Xidong Wu and Zhengmian Hu. Adagda: Faster adaptive gradient descent ascent methods for minimax optimization. The 26th International Conference on Artificial Intelligence and Statistics (AISTATS), 2365-2389, 2023.

[4] Feihu Huang, Shangqian Gao, Jian Pei and Heng Huang, Accelerated Zeroth-Order and First-Order Momentum Methods from Mini to Minimax Optimization, Journal of Machine Learning Research (JMLR), 23:1-70, 2022. (CCF A类)

[5] Feihu Huang, Junyi Li, Shangqian Gao and Heng Huang. Enhanced bilevel optimization via bregman distance. Advances in Neural Information Processing Systems (NeurIPS), 35 : 28928-28939, 2022. (CCF A类)

[6] Feihu Huang, Shangqian Gao and Heng Huang. Bregman Gradient Policy Optimization. International Conference on Learning Representations (ICLR), 2022.

[7] Feihu Huang, Junyi Li and Heng Huang. SUPER-ADAM: Faster and Universal Framework of Adaptive Gradients. Advances in Neural Information Processing Systems (NeurIPS), 34:9074-9085, 2021. (CCF A类)

[8] Feihu Huang, Xidong Wu and Heng Huang. Efficient mirror descent ascent methods for nonsmooth minimax problems. Advances in Neural Information Processing Systems (NeurIPS), 34:10431-10443, 2021. (CCF A类)

[9] Feihu Huang, Shangqian Gao, Jian Pei and Heng Huang. Momentum-Based Policy Gradient Methods. Proceedings of the 37th International Conference on Machine Learning (ICML), 4422-4433, 2020. (CCF A类)

[10] Feihu Huang, Lue Tao and Songcan Chen. Accelerated Stochastic Gradient-free and Projection-free Methods. Proceedings of the 37th International Conference on Machine Learning (ICML), 4519-4530, 2020. (CCF A类)

[11] Feihu Huang, Songcan Chen and Heng Huang. Faster stochastic alternating direction method of multipliers for nonconvex optimization. Proceedings of the 36th International Conference on Machine Learning (ICML), 2839-2848, 2019. (CCF A类)

[12] Feihu Huang, Bin Gu, Zhouyuan Huo, Songcan Chen and Heng Huang. Faster gradient-free proximal stochastic methods for nonconvex nonsmooth optimization. Proceedings of the AAAI Conference on Artificial Intelligence,33(01):1503-1510, 2019. (CCF A类)

[13] Feihu Huang, Shangqian Gao, Songcan Chen and Heng Huang. Zeroth-order stochastic alternating direction method of multipliers for nonconvex nonsmooth optimization. In 28th International Joint Conference on Artificial Intelligence (IJCAI), 2019. (CCF A类)

分布式学习代表性论文： 

[1] Feihu Huang, Xinrui Wang, Junyi Li, Songcan Chen. "Adaptive Federated Minimax Optimization with Lower Complexities." Proceedings of the 27th International Conference on Artificial Intelligence and Statistics (AISTATS) 2024. (已接收)

[2] Junyi Li, Feihu Huang, and Heng Huang. "FedDA: Faster Adaptive Gradient Methods for Federated Constrained Optimization." The Twelfth International Conference on Learning Representations (ICLR) 2024. (https://openreview.net/pdf?id=kjn99xFUF3)

[3] Junyi Li, Feihu Huang, and Heng Huang. "Communication-Efficient Federated Bilevel Optimization with Global and Local Lower Level Problems." Advances in Neural Information Processing Systems (NeurIPS), 36, 2023. (CCF A类)

[4] Xidong Wu, Feihu Huang, Zhengmian Hu, and Heng Huang. "Faster adaptive federated learning." In Proceedings of the AAAI Conference on Artificial Intelligence, vol. 37, no. 9, pp. 10379-10387. 2023. (CCF A类)

[5] Wenhan Xian, Feihu Huang, Yanfu Zhang, and Heng Huang. "A faster decentralized algorithm for nonconvex minimax problems." Advances in Neural Information Processing Systems (NeurIPS), 34: 25865-25877, 2021. (CCF A类)

[6] Wenhan Xian, Feihu Huang, and Heng Huang. "Communication-efficient frank-wolfe algorithm for nonconvex decentralized distributed learning." In Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, no. 12, pp. 10405-10413. 2021. (CCF A类)

大模型轻量化代表性论文：

[1] Shangqian Gao, Yanfu Zhang, Feihu Huang, and Heng Huang, BilevelPruning: Unified Dynamic and Static Channel Pruning for Convolutional Neural Networks, n Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024 (CCF A类)

[2] Shangqian Gao, Zeyu Zhang, Yanfu Zhang, Feihu Huang, and Heng Huang. "Structural Alignment for Network Pruning through Partial Regularization." In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pp. 17402-17412. 2023. (CCF A类)

[3] Shangqian Gao, Feihu Huang, Yanfu Zhang, and Heng Huang. "Disentangled differentiable network pruning." In European Conference on Computer Vision (ECCV), pp. 328-345, 2022.

[4] Shangqian Gao, Feihu Huang, Weidong Cai, and Heng Huang. "Network pruning via performance maximization." In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9270-9280. 2021. (CCF A类)

[5] Shangqian Gao, Feihu Huang, Jian Pei, and Heng Huang. "Discrete model compression with resource constraint for deep neural networks." In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (CVPR), pp. 1899-1908. 2020. (CCF A类)

2024年研究生还有名额，欢迎联系。