一类新的缺失质量的Bernstein型浓度不等式
Novel Bernstein-like Concentration Inequalities for the Missing Mass
摘要:
我们关心的是获得新的浓度不等式的缺失的质量,即总概率质量的结果没有观察到的样本。我们不仅首次导出了无分布的Bernstein类偏差界,其中偏差大小为缺失质量的次线性指数,而且改进了McAllester和Ortiz(2003)以及Berend和Kontorovich(2013,2012)的结果,这是学习理论中最有趣的情况。众所周知,大多数标准不等式不能直接用于分析异质和,即那些项的大小相差很大的和。我们的通用和直观的方法表明,在McAllester和Ortiz(2003)中引入的异质性问题是可以解决的,至少在缺失质量的情况下,通过使用我们的新阈值技术调节的条款。
英文摘要:
We are concerned with obtaining novel concentration inequalities for the missing mass, i.e. the total probability mass of the outcomes not observed in the sample. We not only derive - for the first time - distribution-free Bernstein-like deviation bounds with sublinear exponents in deviation size for missing mass, but also improve the results of McAllester and Ortiz (2003) andBerend and Kontorovich (2013, 2012) for small deviations which is the most interesting case in learning theory. It is known that the majority of standard inequalities cannot be directly used to analyze heterogeneous sums i.e. sums whose terms have large difference in magnitude. Our generic and intuitive approach shows that the heterogeneity issue introduced in McAllester and Ortiz (2003) is resolvable at least in the case of missing mass via regulating the terms using our novel thresholding technique.
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。