Scholar
Zixuan Dong
Google Scholar ID: lbtEL90AAAAJ
New York University
Citations & Impact
Citations
35
H-index
3
i10-index
2
Publications
7
Co-authors
5
list available
Publications
Resume (English only)
Academic Achievements
- Publications:
- 1. George Andriopoulos*, Zixuan Dong*, Li Guo*, Zifan Zhao*, Keith Ross*, “The Prevalence of Neural Collapse in Neural Multivariate Regression”, Accepted by NeurIPS 2024
- 2. Zecheng Wang*, Che Wang*, Zixuan Dong*, Keith Ross, “Pre-training with Synthetic Data Helps Offline Reinforcement Learning”, Accepted by ICLR 2024
- 3. Li Guo, Keith Ross, Zifan Zhao, George Andriopoulos, Shuyang Ling, Yufeng Xu, Zixuan Dong, “Cross Entropy versus Label Smoothing: A Neural Collapse Perspective”, arXiv preprint, 2024
- 4. Zixuan Dong, Che Wang, Keith W. Ross, “On the Convergence of Monte Carlo UCB for Random-Length Episodic MDPs”, arXiv preprint, 2022
- (* Equal Contribution)
Research Experience
- During his undergraduate, he worked with Professor Keith Ross on the convergence property of classic algorithms in tabular RL and Multi-armed Bandit literature.
Education
- Degree: B.Sc.
- School: NYU Shanghai
- Major: Honors Mathematics and Data Science, with a concentration in AI
- Advisor: Professor Keith Ross
- Time: During undergraduate studies
Background
- Research Interests: Application and theory of reinforcement learning (RL) and deep learning, with a focus on enhancing the sample efficiency and generalization of deep RL algorithms. He is a Ph.D. student in Computer Science at NYU Shanghai and NYU Courant.
Miscellany
- Personal Interests: Kendo, Cooking
