{
  "annotation_id": "a6e68788-6de5-4faa-9364-ec3f1d13da8f",
  "date_created": "2026-02-17T05:53:19.894000Z",
  "date_modified": "2026-02-17T05:53:19.894000Z",
  "file_hash": "f844471bae19ce523ac7b98c702af92ee9f77e5479172f99f0998f8658baf8db",
  "private": false,
  "record": {
    "abstract": "This work explores properties of Strong Data-Processing constants for R\\\u0027enyi Divergences. Parallels are made with the well-studied $\\varphi$-Divergences, and it is shown that the order $\\alpha$ of R\\\u0027enyi Divergences dictates whether certain properties of the contraction of $\\varphi$-Divergences are mirrored or not. In particular, we demonstrate that when $\\alpha\u003e1$, the contraction properties can deviate quite strikingly from those of $\\varphi$-Divergences. We also uncover specific characteristics of contraction for the $\\infty$-R\\\u0027enyi Divergence and relate it to $\\varepsilon$-Local Differential Privacy. The results are then applied to bound the speed of convergence of Markov chains, where we argue that the contraction of R\\\u0027enyi Divergences offers a new perspective on the contraction of $L^\\alpha$-norms commonly studied in the literature.",
    "arxiv_id": "2601.09328",
    "authors": [
      "Adrien Vandenbroucque",
      "Amedeo Roberto Esposito",
      "Michael Gastpar"
    ],
    "categories": [
      "cs.IT",
      "math.IT",
      "math.PR"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "title": "Contraction of R\\\u0027enyi Divergences for Discrete Channels: Properties and Applications",
    "url": "https://arxiv.org/abs/2601.09328",
    "version": "v1"
  },
  "schema_id": "dorsal/arxiv",
  "source": {
    "execution_id": "1fadf008-6cb2-4b6b-8878-36619c39d6e8",
    "id": "arXiv Dataset",
    "type": "Model",
    "variant": "snapshot-2026-01-17",
    "version": "0.1.0"
  },
  "user_id": 1000002
}