Tight lower bound on the probability of a binomial exceeding its expectation

Spencer Greenberg, Mehryar Mohri

Research output: Contribution to journalArticlepeer-review

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.

Original languageEnglish (US)
Pages (from-to)91-98
Number of pages8
JournalStatistics and Probability Letters
Volume86
Issue number1
DOIs
StatePublished - Mar 2014

Keywords

  • Binomial distribution
  • Expected value
  • Lower bound
  • Machine learning
  • Relative deviation

ASJC Scopus subject areas

  • Statistics and Probability
  • Statistics, Probability and Uncertainty

Fingerprint Dive into the research topics of 'Tight lower bound on the probability of a binomial exceeding its expectation'. Together they form a unique fingerprint.

Cite this