A refinement of Bennett's inequality with applications to portfolio optimization
This work provides a theoretical improvement in concentration inequalities with applications in finance, but it is incremental as it refines an existing inequality.
The authors introduced a refinement of Bennett's inequality that is strictly tighter than the classical bound, establishing improved convergence rates for averages of independent random variables by leveraging Lambert's W function, and applied it to portfolio optimization for budget allocation across investments with heterogeneous returns.
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.