A refinement of Bennett's inequality is introduced which is strictly tighter than the classical bound. The new bound establishes the convergence of the average of independent random variables to its expected value. It also carefully exploits information about the potentially heterogeneous mean, variance, and ceiling of each random variable. The bound is strictly sharper in the homogeneous setting and very often significantly sharper in the heterogeneous setting. The improved convergence rates are obtained by leveraging Lambert's W function. We apply the new bound in a portfolio optimization setting to allocate a budget across investments with heterogeneous returns.
[1]
Ronald F. Boisvert,et al.
NIST Handbook of Mathematical Functions
,
2010
.
[2]
M. Talagrand.
The missing factor in Hoeffding's inequalities
,
1995
.
[3]
G. Bennett.
Probability Inequalities for the Sum of Independent Random Variables
,
1962
.
[4]
M. Talagrand.
Concentration of measure and isoperimetric inequalities in product spaces
,
1994,
math/9406212.
[5]
W. Hoeffding.
Probability Inequalities for sums of Bounded Random Variables
,
1963
.
[6]
Yu. V. Prokhorov.
An Extremal Problem in Probability Theory
,
1959
.
[7]
Gábor Lugosi,et al.
Introduction to Statistical Learning Theory
,
2004,
Advanced Lectures on Machine Learning.