A Bennett Inequality for the Missing Mass
Machine Learning
2015-12-02 v2
Abstract
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.
Cite
@article{arxiv.1503.06134,
title = {A Bennett Inequality for the Missing Mass},
author = {Bahman Yari Saeed Khanloo},
journal= {arXiv preprint arXiv:1503.06134},
year = {2015}
}
Comments
It is not possible to derive a Bennett inequality using this approach