arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2109.14703cs.LGcs.AIcs.DCcs.MAmath.STstat.TH
收藏

多资源下的序贯估计:一个Bandit观点

Sequential Estimation under Multiple Resources: a Bandit Point of View

Sharif University of Technology(谢里夫理工大学)

Alireza Masoumian, Shayan Kiyani, Mohammad Hossein Yassaee

摘要:

在联邦环境下定义了多资源序贯估计问题。SEMR可以看作是统计估计和强盗理论的交叉点。在这个问题中,一个智能体面对k个资源来估计一个参数$θ$。智能体应该通过明智地选择资源来不断学习资源的质量,最后根据收集的数据提出一个估计器。在本文中,我们假设资源的分布是高斯分布。最终估计量的质量由其均方误差来评估。此外,我们限制我们的类估计无偏估计,以定义一个有意义的概念遗憾。后悔通过最终估计量的方差与最优方差的比较来衡量代理的性能。我们提出了一个下限,以确定的基本限制的设置,即使在这种情况下,分布不是高斯。此外,我们提供了一个顺序优化算法来实现这个下限。

英文摘要:

The problem of Sequential Estimation under Multiple Resources (SEMR) is defined in a federated setting. SEMR could be considered as the intersection of statistical estimation and bandit theory. In this problem, an agent is confronting with k resources to estimate a parameter $θ$. The agent should continuously learn the quality of the resources by wisely choosing them and at the end, proposes an estimator based on the collected data. In this paper, we assume that the resources' distributions are Gaussian. The quality of the final estimator is evaluated by its mean squared error. Also, we restrict our class of estimators to unbiased estimators in order to define a meaningful notion of regret. The regret measures the performance of the agent by the variance of the final estimator in comparison to the optimal variance. We propose a lower bound to determine the fundamental limit of the setting even in the case that the distributions are not Gaussian. Also, we offer an order-optimal algorithm to achieve this lower bound.

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。

↑