Revisiting Concentration of Missing Mass
Statistics Theory
2020-05-25 v3 Machine Learning
Probability
Machine Learning
Statistics Theory
Abstract
We revisit the problem of \emph{missing mass concentration}, developing a new method of estimating concentration of heterogenic sums, in spirit of celebrated Rosenthal's inequality. As a result we slightly improve the state-of-art bounds due to Ben-Hamou at al., and simplify the proofs.
Cite
@article{arxiv.2005.10018,
title = {Revisiting Concentration of Missing Mass},
author = {Maciej Skorski},
journal= {arXiv preprint arXiv:2005.10018},
year = {2020}
}
Comments
Added suplementary materials