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 1709.02707cs.LG
收藏

参数的学习群体

Learning Populations of Parameters

Stanford University(斯坦福大学)

Kevin Tian, Weihao Kong, Gregory Valiant

摘要:

考虑以下估计问题:存在$n$实体,每个实体具有未知参数$p_i \in [0,1]$,并且我们观察$n$独立随机变量$X_1,\ldots,X_n$与$X_i \sim $二项式$(t, p_i)$。如何准确地恢复$p_i$的“直方图”(即累积密度函数)?虽然经验估计将恢复直方图的推土机距离$Θ(\frac{1}{\sqrt{t}})$(相当于,$\ell_1$距离之间的CDF),我们表明,提供$n$是足够大的,我们可以实现误差$O(\frac{1}{t})$,这是信息理论上最优的。我们还将我们的结果扩展到多维参数的情况下,捕捉设置,其中每个成员的人口有多个相关的参数。除了理论结果之外,我们还证明了恢复算法在各种数据集上的实践表现良好,为几个领域提供了启发性的见解,包括政治,体育分析和后代性别比例的变化。

英文摘要:

Consider the following estimation problem: there are $n$ entities, each with an unknown parameter $p_i \in [0,1]$, and we observe $n$ independent random variables, $X_1,\ldots,X_n$, with $X_i \sim $ Binomial$(t, p_i)$. How accurately can one recover the "histogram" (i.e. cumulative density function) of the $p_i$'s? While the empirical estimates would recover the histogram to earth mover distance $Θ(\frac{1}{\sqrt{t}})$ (equivalently, $\ell_1$ distance between the CDFs), we show that, provided $n$ is sufficiently large, we can achieve error $O(\frac{1}{t})$ which is information theoretically optimal. We also extend our results to the multi-dimensional parameter case, capturing settings where each member of the population has multiple associated parameters. Beyond the theoretical results, we demonstrate that the recovery algorithm performs well in practice on a variety of datasets, providing illuminating insights into several domains, including politics, sports analytics, and variation in the gender ratio of offspring.

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。

↑