Preliminary Empirical Study of Low-Rank, Hierarchical Gaussian Linear Bandits
Abstract
Inspired by recent advances in multi-task bandits, we propose a new problem setting called low-rank, hierarchical Gaussian linear bandits, which combines low-rank structure with the hierarchical Bayesian approach. We extend the hierarchical Thompson sampling of Hong et al. [8] to our setting by combining it with Gibbs Sampling and show its efficacy empirically.
Junghyun Lee
PhD Student
PhD student at GSAI, KAIST, jointly advised by Profs. Se-Young Yun and Chulhee Yun. Research focuses on interactive machine learning, “theoretical perspectives” of LLMs, optimization theory, and statistical analyses of large networks with an emphasis on community detection. Broadly interested in mathematical and theoretical AI, as well asrelated problems in mathematics and statistics.