Tight Lower Bound on the Probability of a Binomial Exceeding its Expectation
Machine Learning
2013-11-12 v3 Machine Learning
Abstract
We give the proof of a tight lower bound on the probability that a binomial random variable exceeds its expected value. The inequality plays an important role in a variety of contexts, including the analysis of relative deviation bounds in learning theory and generalization bounds for unbounded loss functions.
Cite
@article{arxiv.1306.1433,
title = {Tight Lower Bound on the Probability of a Binomial Exceeding its Expectation},
author = {Spencer Greenberg and Mehryar Mohri},
journal= {arXiv preprint arXiv:1306.1433},
year = {2013}
}