Tight Lower Bound on the Probability of a Binomial Exceeding its Expectation

06/06/2013
by   Spencer Greenberg, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/18/2023

A Tight Lower Bound for Compact Set Packing

This note is devoted to show a simple proof of a tight lower bound of th...
research
12/21/2017

Bounds on the Entropy of a Function of a Random Variable and their Applications

It is well known that the entropy H(X) of a discrete random variable X i...
research
03/13/2013

Generalizing Jeffrey Conditionalization

Jeffrey's rule has been generalized by Wagner to the case in which new e...
research
08/24/2022

Towards a Lower Bound for the Average Case Runtime of Simulated Annealing on TSP

We analyze simulated annealing (SA) for simple randomized instances of t...
research
10/29/2021

Improving Generalization Bounds for VC Classes Using the Hypergeometric Tail Inversion

We significantly improve the generalization bounds for VC classes by usi...
research
05/26/2023

An Analysis of the Johnson-Lindenstrauss Lemma with the Bivariate Gamma Distribution

Probabilistic proofs of the Johnson-Lindenstrauss lemma imply that rando...
research
10/19/2012

Practically Perfect

The property of perfectness plays an important role in the theory of Bay...

Please sign up or login with your details

Forgot password? Click here to reset