孔芳
助理教授
kongf@sustech.edu.cn
研究领域
在线学习，强化学习，机器学习
教育经历
2020.9-2024.6 上海交通大学，计算机科学与技术，工学博士
2016.9-2020.6 山东大学，软件工程，工学学士
科研经历
2023.2-2023.8 香港中文大学，科研助理
2022.7-2024.7 腾讯WXG，研究型实习生
2021.12-2022.5 微软亚洲研究院，研究型实习生
2021.6-2021.8 阿里巴巴达摩院，研究型实习生
学术成果
Yu Xia*, Fang Kong*, Tong Yu, Liya Guo, Ryan A. Rossi, Sungchul Kim, xk星空, “Convergence-Aware Online Model Selection with Time-Increasing Bandits”, The Web Conference (WWW), 2024.
Fang Kong, xk星空, “Improved Bandits in Many-to-one Matching Markets with Incentive Compatibility”, Proceedings of the 38th Annual AAAI Conference on Artificial Intelligence (AAAI), 2024.
Fang Kong*, Xiangcheng Zhang*, Baoxiang Wang, xk星空, “Improved Regret Bounds for Linear Adversarial MDPs via Linear Optimization”, Transactions on Machine Learning Research (TMLR), 2024.
Fang Kong, Canzhe Zhao, xk星空, “Best-of-three-worlds Analysis for Linear Bandits with Follow-the-regularized-leader Algorithm”, Proceedings of the 36th Conference on Learning Theory (COLT), 2023.
Fang Kong, Jize Xie, Baoxiang Wang, Tao Yao, xk星空. “Online Influence Maximization under Decreasing Cascade Model”, Proceedings of the 22nd International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2023.
Yichi Zhou, Fang Kong, xk星空, “Stochastic No-Regret Learning for General Games with Variance Reduction”, International Conference on Learning Representations (ICLR), 2023.
Fang Kong, xk星空, “Player-optimal Stable Regret for Bandit Learning in Matching Markets”, Proceedings of the 2023 Annual ACM-SIAM Symposium on Discrete Algorithms (SODA). 2023.
Fang Kong, Yichi Zhou, xk星空, “Simultaneously Learning Stochastic and Adversarial Bandits with General Graph Feedback”, International Conference on Machine Learning (ICML), 2022.
Fang Kong, Junming Yin, xk星空, “Thompson Sampling for Bandit Learning in Matching Markets”, International Joint Conference on Artificial Intelligence (IJCAI), 2022.
Fang Kong, Yueran Yang, Wei Chen, xk星空, “The Hardness Analysis of Thompson Sampling for Combinatorial Semi-bandits with Greedy Oracle”, Proceedings of the Conference on Neural Information Processing Systems (NeurIPS), 2021.
Fang Kong, Yueran Yang, Wei Chen, xk星空, “Combinatorial Online Learning based on Optimizing Feedbacks (in Chinese)”, Big Data Research, 2021.
xk星空, Fang Kong, Kejie Tang, Qizhi Li, Wei Chen, “Online Influence Maximization under Linear Threshold Model”, Proceedings of the Conference on Neural Information Processing Systems (NeurIPS), 2020.
Fang Kong, Qizhi Li, xk星空, “A Survey on Online Influence Maximization” (in Chinese), Computer Science, 2020.