Yingru Li
Yingru Li
Home
Talks
Publications
Contact
Resume
RL-Seminar
Light
Dark
Automatic
Martingale
Probability Tools for Sequential Random Projection
First probabilistic framework for sequential random projection, an approach rooted in the challenges of sequential decision-making under uncertainty; A non-trivial martingale extension of Johnson-Lindenstrauss (JL) to sequentially adaptive data processes.
Yingru Li
Cite
arXiv
Provably scalable and near-optimal Thompson sampling via hypermodel with applications in decision-making language agents
Hypermodel for efficient incremental approximation of the posterior (uncertainty quantification) over complex models without leveraging conjugacy as encountering more data; Index sampling for approximate posterior sampling for data-efficient sequential decision-making. This approach is provably superior than ensemble sampling and Langevin Monte-carlo.
Yingru Li
,
Jiawei Xu
,
Zhi-Quan Luo
Cite
Efficient and scalable reinforcement learning via hypermodel
Addressing efficiency challenge in RL with theoretical advancements and practical algorithm designs.
Yingru Li
,
Jiawei Xu
,
Zhiquan Luo
PDF
Cite
Poster
Slides
Website
Cite
×