Abstract
This work explores properties of Strong Data-Processing constants for Rényi Divergences. Parallels are made with the well-studied -Divergences, and it is shown that the order of Rényi Divergences dictates whether certain properties of the contraction of -Divergences are mirrored or not. In particular, we demonstrate that when , the contraction properties can deviate quite strikingly from those of -Divergences. We also uncover specific characteristics of contraction for the -Rényi Divergence and relate it to -Local Differential Privacy. The results are then applied to bound the speed of convergence of Markov chains, where we argue that the contraction of Rényi Divergences offers a new perspective on the contraction of -norms commonly studied in the literature.
Connections
Explore this paper’s authors, topics and related work.
Building this map preview
BZPEER is loading the nearby papers, people, topics and institutions for this page.
Reviews 0
Write a review
No reviews yet.
Discussion 0
Add a comment
No comments yet.