Theoretical Analyses of Reinforcement Learning with Human Feedback (RLHF) and Related Problems
Logistic and Generalized Linear Bandits, Dueling Bandits, etc.
Project #2. A Unified Confidence Sequence for Generalized Linear Models, with Applications to Bandits
- Accepted to NeurIPS 2024.
- Accepted to ICML 2024 Workshop on Aligning Reinforcement Learning Experimentalists and Theorists (ARLET) as oral.
- Joint work with Se-Young Yun (KAIST AI) and Kwang-Sung Jun (Univ. of Arizona CS).
Project #1. Improved Regret Bounds of (Multinomial) Logistic Bandits via Regret-to-Confidence-Set Conversion
- Accepted to AISTATS 2024.
- Joint work with Se-Young Yun (KAIST AI) and Kwang-Sung Jun (Univ. of Arizona CS).
``General’’ Theoretical Questions in RLHF
Junghyun Lee
PhD Student
PhD student at GSAI, KAIST, jointly advised by Prof. Se-Young Yun and Prof. Chulhee Yun. Interested in mathematical and theoretical AI, i.e., essentially any machine learning challenges necessitating mathematical analysis. Recently focused on statistical problems arising from RLHF, including interactive machine learning and low-dimensional structure recovery.
