高维决策,上界和下界
High Dimensional Decision Making, Upper and Lower Bounds
摘要:
决策者的效用取决于他的行动$a\in A \subset \mathbb{R}^d$和与世界$θ\in Θ$相关的收益状态。人们可以将获取新信息的价值定义为信息获取前后的最大期望效用之差。在本文中,我发现渐近结果的期望值的信息$d \to \infty$,通过使用工具的理论(子)高斯过程和一般的链接。
英文摘要:
A decision maker's utility depends on her action $a\in A \subset \mathbb{R}^d$ and the payoff relevant state of the world $θ\in Θ$. One can define the value of acquiring new information as the difference between the maximum expected utility pre- and post information acquisition. In this paper, I find asymptotic results on the expected value of information as $d \to \infty$, by using tools from the theory of (sub)-Guassian processes and generic chaining.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。