Tight lower bound on the probability of a binomial exceeding its expectation
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.
Year of publication: |
2014
|
---|---|
Authors: | Greenberg, Spencer ; Mohri, Mehryar |
Published in: |
Statistics & Probability Letters. - Elsevier, ISSN 0167-7152. - Vol. 86.2014, C, p. 91-98
|
Publisher: |
Elsevier |
Subject: | Binomial distribution | Lower bound | Expected value | Relative deviation | Machine learning |
Saved in:
Online Resource
Saved in favorites
Similar items by subject
-
Is Q-learning minimax optimal? : a tight sample complexity analysis
Li, Gen, (2024)
-
Comparative analysis of government debt in the European Union's member states, 2000 - 2013
Talpoş, Ioan, (2014)
-
Lee, Jungjin, (2009)
- More ...