Fang Kong

I am a fourth-year Ph.D. candidate in John Hopcroft Center, Shanghai Jiao Tong University, fortunate to be advised by Prof. Shuai Li. I am also a member in Wu Honor Ph.D. Class in Artificial Intelligence starting from Autumn 2020. Before joining SJTU, I obtained my bachelor degree in Software engineering from Shandong University (1/318).

I am interested in bandit theory and reinforcement learning theory, aiming at providing theoretically guaranteed algorithms. My current research topics include the problem of online matching markets, bandits with graph feedback, and combinatorial bandits. I am also interested in applications of bandit algorithms such as online experimentation.

Email  /  CV  /  GoogleScholar /  DBLP /  GitHub

profile photo
Publications  (* denotes equal contribution)
Improved Bandits in Many-to-one Matching Markets with Incentive Compatibility
Fang Kong and Shuai Li.
Accepted by AAAI, 2024  
Improved Regret Bounds for Linear Adversarial MDPs via Linear Optimization
Fang Kong*, Xiangcheng Zhang*, Baoxiang Wang and Shuai Li.
Accepted by Transactions on Machine Learning Research (TMLR), 2024  
Best-of-three-worlds Analysis for Linear Bandits with Follow-the-regularized-leader Algorithm [arXiv]
Fang Kong, Canzhe Zhao and Shuai Li.
Proceedings of 36th Conference on Learning Theory (COLT), 2023  
Online Influence Maximization under Decreasing Cascade Model [arXiv]
Fang Kong, Jize Xie, Baoxiang Wang, Tao Yao and Shuai Li.
Proceedings of the 22nd International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2023  
Stochastic No-Regret Learning for General Games with Variance Reduction
Yichi Zhou, Fang Kong and Shuai Li.
Proceedings of the 11th International Conference on Learning Representations (ICLR), 2023  
Player-optimal Stable Regret for Bandit Learning in Matching Markets [arXiv] [slides]
Fang Kong and Shuai Li
Proceedings of the 34th Annual ACM-SIAM Symposium on Discrete Algorithms (SODA), 2023  
Simultaneously Learning Stochastic and Adversarial Bandits with General Graph Feedback [arXiv] [slides]
Fang Kong, Yichi Zhou and Shuai Li
Proceedings of the 39th International Conference on Machine Learning (ICML), 2022  
Thompson Sampling for Bandit Learning in Matching Markets [arXiv]
Fang Kong, Junming Yin and Shuai Li
Proceedings of the 31st International Joint Conference on Artificial Intelligence (IJCAI), 2022  
The Hardness Analysis of Thompson Sampling for Combinatorial Semi-bandits with Greedy Oracle [arXiv] [slides] [poster]
Fang Kong, Yueran Yang, Wei Chen and Shuai Li
Proceedings of the 35th Conference on Neural Information Processing Systems (NeurIPS), 2021  
Combinatorial Online Learning based on Optimizing Feedbacks (in Chinese)
Fang Kong, Yueran Yang, Wei Chen and Shuai Li
Big Data Research, 2021  
Online Influence Maximization under Linear Threshold Model [arXiv][slides][poster]
Shuai Li, Fang Kong, Kejie Tang, Qizhi Li and Wei Chen.
Proceedings of the 34th Conference on Neural Information Processing Systems (NeurIPS), 2020  
A Survey on Online Influence Maximization  (in Chinese)
Fang Kong, Qizhi Li and Shuai Li
Computer Science, 2020  
Internships and Research Experiences
Intern at Tencent WXG as a member of the Tencent Rhino-Bird Research Elite Program, Shenzhen, China. 2022.7-present
Visiting student of Prof. John C.S. Lui at the Chinese University of Hong Kong, Hong Kong, China. 2023.2-2023.8
Research Intern of Dr. Yichi Zhou at Microsoft Research Asia (MSRA), Beijing, China. 2021.12-2022.5
Research Intern of Dr. Xue Wang and Dr. Tao Yao at Alibaba DAMO Academy, Hangzhou, China. 2021.6-2021.8
Talks
"Best-of-three-worlds Analysis for Linear Bandits with Follow-the-regularized-leader Algorithm"
Female Forum in IJTCS-FAW, Macau, China

2023.8
"Online Influence Maximization under Decreasing Cascade Model"
AAMAS, London, UK

2023.6
"Player-optimal Stable Regret for Bandit Learning in Matching Markets"
SODA, Online
Seminar in School of Data Science, CUHK-SZ, Shenzhen, China

2023.1
2022.11
"The Hardness Analysis of Thompson Sampling for Combinatorial Semi-bandits with Greedy Oracle"
Outstanding Doctoral Forum in John Hopcroft Center, SJTU, Shanghai, China

2022.1
"Online Influence Maximization under Linear Threshold Model"
Outstanding Doctoral Forum in John Hopcroft Center, SJTU, Shanghai, China

2020.12
Awards
  • National Scholarship (for Ph.D. students), from the ministry of Education of China, 2023,2022
  • AAMAS Student Scholarship, 2023
  • Award of Excellence in Stars of Tomorrow Internship Program, Microsoft Research Asia, 2022
  • First Prize for Outstanding Ph.D. Student, John Hopcroft Center, Shanghai Jiao Tong University, 2022
  • Wu Wen Jun Honorary Doctoral Scholarship, 2020
  • Outstanding Graduates of Shandong Province, 2020
  • Honors Bachelor of Shandong University, 2020
  • Outstanding Undergraduate Thesis of Shandong University, 2020
  • National Scholarship (for undergraduate students), from the ministry of Education of China, 2018,2017
  • First-class scholarship for outstanding students in Shandong University, 2018,2017
Professional Services
Conference Reviewer for
  • International Conference on Machine Learning (ICML), 2023-2022
  • Conference on Neural Information Processing Systems (NeurIPS), 2023-2021

Teaching Assistantships
  • AI3601 Reinforcement Learning (Undergraduate), SJTU, Spring 2023
  • CS3317 Artificial Intelligence (Undergraduate), SJTU, Fall 2022
  • CS445 Combinatorics (Undergraduate), SJTU, Fall 2021
  • CS410 Artificial Intelligence (Undergraduate), SJTU, Fall 2020