arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1503.06134stat.ML
收藏

缺少质量的Bennett不等式

A Bennett Inequality for the Missing Mass

Bahman Yari Saeed Khanloo

摘要:

新的集中不等式得到的缺失质量,即总概率质量的结果没有观察到的样本。我们导出了无分布偏差界,其中偏差大小为缺失质量的次线性指数,并改进了Berend和Kontorovich(2013)以及Yari Saeed Khanloo和Haffari(2015)的结果,用于小偏差,这是学习理论中最重要的情况。

英文摘要:

Novel concentration inequalities are obtained for the missing mass, i.e. the total probability mass of the outcomes not observed in the sample. We derive distribution-free deviation bounds with sublinear exponents in deviation size for missing mass and improve the results of Berend and Kontorovich (2013) and Yari Saeed Khanloo and Haffari (2015) for small deviations which is the most important case in learning theory.

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。

↑