BriefGPT.xyz
Feb, 2023
私人和强健赌博机
On Private and Robust Bandits
HTML
PDF
Yulian Wu, Xingyu Zhou, Youming Tao, Di Wang
TL;DR
研究私有和强健的多臂赌博机，提出了一种私密且强健的平均估计子例程，基于奖励截断和拉普拉斯机制，旨在实现评估精度、隐私和鲁棒性三者之间的最佳平衡。
Abstract
We study
private and robust multi-armed bandits
(MABs), where the agent receives
huber's contaminated heavy-tailed rewards
and meanwhile needs to ensure
→