Sharp Concentration Inequalities for the Centered Relative Entropy

TL;DR

This paper establishes sharp concentration inequalities for the centered relative entropy between empirical and true discrete distributions, providing precise confidence bounds under certain conditions.

Contribution

It introduces new concentration bounds for the centered relative entropy that are optimal up to logarithmic factors, improving understanding of empirical distribution deviations.

Findings

Derived upper bounds on the moment generating function of the centered relative entropy.

Established sharp concentration inequalities for the centered relative entropy.

Provided confidence intervals and moment bounds that are nearly optimal.

Abstract

We study the relative entropy between the empirical estimate of a discrete distribution and the true underlying distribution. If the minimum value of the probability mass function exceeds an $\alpha > 0$ (i.e. when the true underlying distribution is bounded sufficiently away from the boundary of the simplex), we prove an upper bound on the moment generating function of the centered relative entropy that matches (up to logarithmic factors in the alphabet size and $\alpha$) the optimal asymptotic rates, subsequently leading to a sharp concentration inequality for the centered relative entropy. As a corollary of this result we also obtain confidence intervals and moment bounds for the centered relative entropy that are sharp up to logarithmic factors in the alphabet size and $\alpha$.