Milan Vojnović

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
Theoretical Analyses of Reinforcement Learning with Human Feedback (RLHF) and Related Problems
(tbd)
Junghyun Lee