Dongxie Wen is currently a third-year Ph.D. student at the Gaoling School of Artificial Intelligence, Renmin University of China, under the supervision of Prof. Zhewei Wei. Prior to this, he received his B.Sc. degree in Mathematical Statistics from the School of Statistics at Renmin University of China in June 2023.

Research Interests

My research centers on Sketch4ML, where I focus on designing memory- and computationally-efficient data structures tailored for a variety of learning paradigms. My broader research interests encompass efficient reinforcement learning, online learning, and unlearning. I am also deeply engaged in exploring the complexity and lower bounds of streaming algorithms.

Publications

• Matrix Sketching in Bandits: Current Pitfalls and New Framework
  Dongxie Wen, Hanyan Yin, Xiao Zhang, Zhewei Wei.
  ArXiv. [Paper]

• Fast Second-Order Online Kernel Learning through Incremental Matrix Sketching and Decomposition
  Dongxie Wen, Xiao Zhang*, Zhewei Wei*, Chenping Hou, Shuai Li, Weinan Zhang.
  In IJCAI, 2025. [Paper] [Blog]

• Optimal Matrix Sketching over Sliding Windows (Best Paper Candidate Award).
  Hanyan Yin, Dongxie Wen, Jiajun Li, Zhewei Wei*, Xiao Zhang, Zengfeng Huang, Feifei Li.
  In VLDB, 2024. [Paper] [Code] [Award]