Mr. Yingru Li is a Ph.D. Candidate in the Chinese University of Hong Kong (CUHK), Shenzhen, China. Fortunately, he is advised by Zhi-Quan (Tom) Luo. He received the bachelor degree in Computer Science (ACM Honors Program) from Huazhong University of Science and Technology with an advisory of Kun He. He was a research visiting student at Cornell University with John E. Hopcroft. His Ph.D. research is supported by SRIBD Scholarship, Presidential Fellowship and Tencent Ph.D. Fellowship.
He organized RL Seminar in CUHK-SZ from 2019 to 2022.
NeurIPS 2023, New Orleans 🚀 My research in RL encompasses both theoretical aspects of high-dim probability and practical applications in Deep RL. I have developed a novel random projection tool for sequentially dependent data, which extends the Johnson–Lindenstrauss lemma in a non-trivial way and effectively addresses efficiency challenges in RL. 🚀
Ph.D. in Computer and Information Engineering., 2018 --
The Chinese University of Hong Kong
B.Eng. in Computer Science (Honors Program). Outstanding Graduate, 2017
Huazhong University of Science and Technology, China
We have developed a novel random projection tool for sequentially dependent data, which extends the Johnson–Lindenstrauss lemma in a non-trivial way. Wi th this novel analytical tool, we prove approximate Thompson sampling (TS) with hypermodel can achieve the same regret order of TS with exponential smaller computation requirement than the ensemble sampling. This result effectively addresses data and computation efficiency challenges in online decision-making (bandit and RL), bridging theory and practice.