Kwang-Sung Jun

GL-LowPopArt: A Nearly Instance-Wise Minimax Estimator for (Adaptive) Generalized Linear Low-Rank Trace Regression
We present GL-LowPopArt, a novel Catoni-style estimator for generalized linear low-rank trace regression. Building on LowPopArt (Jang …
Junghyun Lee, Kyoungseok Jang, Kwang-Sung Jun, Milan Vojnović, Se-Young Yun
PDF Cite Project
GL-LowPopArt: A Nearly Instance-Wise Minimax Estimator for (Adaptive) Generalized Linear Low-Rank Trace Regression
A Unified Confidence Sequence for Generalized Linear Models, with Applications to Bandits
We present a unified likelihood ratio-based confidence sequence (CS) for any (self-concordant) generalized linear model (GLM) that is …
Junghyun Lee, Se-Young Yun, Kwang-Sung Jun
PDF Cite Code Project Poster Slides
A Unified Confidence Sequence for Generalized Linear Models, with Applications to Bandits
Improved Regret Bounds of (Multinomial) Logistic Bandits via Regret-to-Confidence-Set Conversion
Logistic bandit is a ubiquitous framework of modeling users’ choices, e.g., click vs. no click for advertisement recommender …
Junghyun Lee, Se-Young Yun, Kwang-Sung Jun
PDF Cite Code Project Poster Slides
Improved Regret Bounds of (Multinomial) Logistic Bandits via Regret-to-Confidence-Set Conversion
Theoretical Analyses of Reinforcement Learning with Human Feedback (RLHF) and Related Problems
(tbd)
Junghyun Lee