Central Limit Theorem for R\'enyi Divergence of Infinite Order

Abstract

For normalized sums $Z_n$ of i.i.d. random variables, we explore necessary and sufficient conditions which guarantee the normal approximation with respect to the R\'enyi divergence of infinite order. In terms of densities $p_n$ of $Z_n$, this is a strengthened variant of the local limit theorem taking the form $\sup_x (p_n(x) - \varphi(x))/\varphi(x) \rightarrow 0$ as $n \rightarrow \infty$.