2 papers
stat.ML2025
Precise Asymptotics and Refined Regret of Variance-Aware UCB
Yingying Fan, Yuxuan Han, Jinchi Lv +2
In this paper, we study the behavior of the Upper Confidence Bound-Variance (UCB-V) algorithm for the Multi-Armed Bandit (MAB) problems, a variant of the canonical Upper Confidence…
stat.ML2025
Asymptotic FDR Control with Model-X Knockoffs: Is Moments Matching Sufficient?
Yingying Fan, Lan Gao, Jinchi Lv +1
We propose a unified theoretical framework for studying the robustness of the model-X knockoffs framework by investigating the asymptotic false discovery rate (FDR) control of the…