Rényi Resolvability, Noise Stability, and Anti-contractivity

As indicated by the title, this paper investigates three closely related topics -- R\'enyi resolvability, noise stability, and anti-contractivity. The R\'enyi resolvability problem refers to approximating a target output distribution of a given channel in the R\'enyi divergence when the input is set to a function of a given uniform random variable. This problem for the R\'enyi parameter in $[0,2]\cup{\infty}$ was studied by the present author and Tan in 2019. In the present paper, we provide a complete solution to this problem for the R\'enyi parameter in the entire range $\mathbb{R}\cup{\pm\infty}$. We then connect the R\'enyi resolvability problem to the noise stability problem, by observing that the $q$-stability of a set can be expressed in terms of the R\'enyi divergence between the true output distribution and the target distribution in a variant of the R\'enyi resolvability problem. By such a connection, we provide sharp dimension-free bounds on the $q$-stability. We lastly relate the noise stability problem to the anti-contractivity of a Markov operator (i.e., conditional expectation operator), where anti-contractivity introduced by us refers to as the opposite property of the well-known contractivity/hyercontractivity. We derive sharp dimension-free anti-contractivity inequalities. All of the results in this paper are evaluated for binary distributions. Our proofs in this paper are mainly based on the method of types, especially strengthened versions of packing-covering lemmas.