Guanghui Wang @ NJUCS

Currently I am second year graduate student of Department of Computer Science and Technology in Nanjing University and a member of LAMDA Group , led by professor Zhi-Hua Zhou.

Supervisor

Associate professor Lijun Zhang.

Biography

I received my B.Sc. degree from Xidian University in June 2017. In the same year, I was admitted to study for a M.Sc. degree in Nanjing University without entrance examination.

Research Interest

My research interests include: Machine Learning, Online Learning, Stochastic Optimization, Data Mining.

Preprints

G. Wang, S. Lu, W. Tu and L. Zhang. SAdam: A Variant of Adam for Strongly Convex Functions. [arXiv]

L. Zhang, G. Wang, W. Tu and Z.-H. Zhou. Dual Adaptivity: A Universal Algorithm for Minimizing the Adaptive Regret of Convex Functions. [arXiv]



Publication

G. Wang, S. Lu, and L. Zhang. Adaptivity and Optimality: A Universal Algorithm for Online Convex Optimization. In Proceedings of the 35nd Conference on Uncertainty in Artificial Intelligence (UAI19), to appear, 2019. [arXiv] [supp]


S. Lu, G. Wang, Y. Hu, and L. Zhang. Multi-Objective Generalized Linear Bandits. In Proceedings of the 28th International Joint Conference on Artificial Intelligence (IJCAI19), to appear, 2019.


S. Lu, G. Wang, Y. Hu, and L. Zhang. Optimal Algorithms for Lipschitz Bandits with Heavy-tailed Rewards. In Proceedings of the 36th International Conference on Machine Learning (ICML19), to appear, 2019.


G. Wang, D. Zhao, and L. Zhang. Minimizing Adaptive Regret with One Gradient per Iteration. In Proceedings of the 27th International Joint Conference on Artificial Intelligence (IJCAI18). [PDF]