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 1411.4342stat.MLcs.AIcs.LG
收藏

机器学习的影响函数:熵、散度和互信息的非参数估计

Influence Functions for Machine Learning: Nonparametric Estimators for Entropies, Divergences and Mutual Informations

Carnegie Mellon University(卡内基梅隆大学);Harvard University(哈佛大学)

Kirthevasan Kandasamy, Akshay Krishnamurthy, Barnabas Poczos, Larry Wasserman, James M. Robins

摘要:

我们提出并分析了非参数假设下一个或多个分布的统计泛函的估计量。我们的估计是基于理论的影响函数,出现在半参数统计文献。我们发现,估计的基础上,无论是数据分裂或留一法技术享受快速收敛速度和其他有利的理论属性。我们应用这个框架来获得几个流行的信息理论量的估计,并通过实证评估,显示这种方法比现有的估计的优势。

英文摘要:

We propose and analyze estimators for statistical functionals of one or more distributions under nonparametric assumptions. Our estimators are based on the theory of influence functions, which appear in the semiparametric statistics literature. We show that estimators based either on data-splitting or a leave-one-out technique enjoy fast rates of convergence and other favorable theoretical properties. We apply this framework to derive estimators for several popular information theoretic quantities, and via empirical evaluation, show the advantage of this approach over existing estimators.

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。

↑