信息设计者可从用户行为中快速学习未知先验，实现接近最优的决策。
Information Design with Unknown Prior
- 通过反复交互，从接收者行为推断其未知先验信念
- 在一般情况下达到 Θ(log T) 的紧致后悔上界，二元动作下为 Θ(log log T)
- 适用于平台等信息设计者，尤其适合动态调整策略的场景
信息设计者（如在线平台）通常不了解接收者的信念。本文设计了学习算法，使信息设计者能通过重复交互从接收者的行为中学习其先验信念。所提出的算法在已知先验下的最优性方面实现了无遗憾，且收敛速度很快：一般情况下后悔上界为 Θ(log T)，在二元动作这一重要特殊情形下为 Θ(log log T)，均为紧致界。
原文摘要 · Abstract (English)
Information designers, such as online platforms, often do not know the beliefs of their receivers. We design learning algorithms so that the information designer can learn the receivers' prior belief from their actions through repeated interactions. Our learning algorithms achieve no regret relative to the optimality for the known prior at a fast speed, achieving a tight regret bound $Θ(\log T)$ in general and a tight regret bound $Θ(\log \log T)$ in the important special case of binary actions.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。