arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv math/0410074math.STstat.TH
收藏

贝叶斯决策论的渐近全局鲁棒性

Asymptotic global robustness in bayesian decision theory

Christophe Abraham, Benoit Cadre

摘要:

在贝叶斯决策论中,已知关于损失和先验的鲁棒性可以通过添加新的观测来提高。在这篇文章中,我们研究了鲁棒性改善率相对于观测数n。考虑了后验全局鲁棒性的三个常用度量:一类损失函数的Bayes动作集的范围,当主观损失属于给定类时使用特定损失的最大后悔,以及当损失函数在一类范围内时后验期望损失的范围.我们表明,收敛速率的鲁棒性的第一个措施是\sqrtn,而其他措施的合理假设下的类损失函数。我们首先研究两个特殊的情况来说明我们的结果。

英文摘要:

In Bayesian decision theory, it is known that robustness with respect to the loss and the prior can be improved by adding new observations. In this article we study the rate of robustness improvement with respect to the number of observations n. Three usual measures of posterior global robustness are considered: the (range of the) Bayes actions set derived from a class of loss functions, the maximum regret of using a particular loss when the subjective loss belongs to a given class and the range of the posterior expected loss when the loss function ranges over a class. We show that the rate of convergence of the first measure of robustness is \sqrtn, while it is n for the other measures under reasonable assumptions on the class of loss functions. We begin with the study of two particular cases to illustrate our results.

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。

↑