arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1902.00746math.STcs.LGstat.MLstat.TH
收藏

关于多武装土匪中样本均值的偏差、风险和一致性

On the bias, risk and consistency of sample means in multi-armed bandits

Carnegie Mellon University(卡内基梅隆大学)

Jaehyeok Shin, Aaditya Ramdas, Alessandro Rinaldo

摘要:

样本均值是统计学中研究最多的估计量之一,具有许多理想的性质,如无偏性和一致性。然而,当分析使用多臂强盗(MAB)实验收集的数据时,样本均值是有偏差的,并且关于其性质仍有许多有待理解。例如,它什么时候是一致的,它的偏差有多大,我们能限制它的均方误差吗?本文对MAB样本均值的偏倚、风险和一致性进行了全面、系统的处理。具体来说,我们确定了四个不同的来源选择偏差(采样,停止,选择和倒带),并分别和一起分析它们。我们进一步证明了一个新的概念\emph{effective sample size}可以用来限制风险的样本均值下适当的损失函数。我们提出了几个精心设计的例子,以提供我们研究的选择偏差的不同来源的直觉。我们的处理是非参数和算法不可知的,这意味着它不依赖于特定的算法或目标。简而言之,我们的证明结合了变分表示的信息理论的分歧与新的鞅浓度不等式。

英文摘要:

The sample mean is among the most well studied estimators in statistics, having many desirable properties such as unbiasedness and consistency. However, when analyzing data collected using a multi-armed bandit (MAB) experiment, the sample mean is biased and much remains to be understood about its properties. For example, when is it consistent, how large is its bias, and can we bound its mean squared error? This paper delivers a thorough and systematic treatment of the bias, risk and consistency of MAB sample means. Specifically, we identify four distinct sources of selection bias (sampling, stopping, choosing and rewinding) and analyze them both separately and together. We further demonstrate that a new notion of \emph{effective sample size} can be used to bound the risk of the sample mean under suitable loss functions. We present several carefully designed examples to provide intuition on the different sources of selection bias we study. Our treatment is nonparametric and algorithm-agnostic, meaning that it is not tied to a specific algorithm or goal. In a nutshell, our proofs combine variational representations of information-theoretic divergences with new martingale concentration inequalities.

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。

↑