Metraipolis › archive › dc_f9325f2685ff

Contraction of Rényi Divergences for Discrete Channels — arXiv:2609.34570

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.34570
License (as archived)
CC0-1.0
Archived
2026-10-07T23:23:53.919Z
SHA-256 of the archived text
11b8a2a1d19292c1b69a51df9ad4190690416475a48b2016a356cd9be051c28e
Stable URL of this page
https://metraipolis.com/documento/dc_f9325f2685ff

How to cite

Contraction of Rényi Divergences for Discrete Channels — arXiv:2609.34570 — arXiv (en), https://arxiv.org/abs/2609.34570 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f9325f2685ff (Metraipolis archive dc_f9325f2685ff, sha256 11b8a2a1d19292c1b69a51df9ad4190690416475a48b2016a356cd9be051c28e)
BibTeX
@misc{dcf9325f2685ff,
  title = {Contraction of Rényi Divergences for Discrete Channels — arXiv:2609.34570},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.34570},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f9325f2685ff; sha256 11b8a2a1d19292c1b69a51df9ad4190690416475a48b2016a356cd9be051c28e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.34570. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We investigate Strong Data-Processing Inequality (SDPI) constants for Rényi Divergences on finite spaces. We study their dependence on the Rényi order $\alpha$, proving that they are non-decreasing and that their scaling by $(\alpha-1)$ is convex for $\alpha\geq1$. We also identify several support restrictions on the probability measures involved in determining these constants. In particular, in the distribution-independent setting, measures supported on a common set of at most two points suffice to evaluate the Rényi-SDPI constant. For $\alpha\in[0,1]$, we further prove equality with the $\chi^2$-SDPI constant, while at order infinity we obtain a closed-form expression. In order to link contraction over product spaces to contraction along individual coordinates, we provide tensorisation bounds for arbitrary product channels analogous to those known for $\varphi$-Divergences. At finite orders, the Rényi-SDPI constants are bounded above and below through comparisons with the $\chi^2$-Divergence and Hellinger Divergences, with sharpness established in multiple cases. At order infinity, we instead relate these constants to the contraction of Total Variation Distance. Finally, our findings are applied to local differential privacy (LDP) and the analysis of Markov chains. This yields sharp contraction guarantees for pure-LDP mechanisms, and connects Rényi-LDP to Rényi-SDPI constants. For Markov chains, we derive finite-time convergence bounds and exhibit a family of chains for which Rényi-SDPIs improve on classical $\chi^2$-based bounds by arbitrarily large factors.

Tema degli esploratori: matematica e informatica teorica (retro-catalogo arXiv: annunci del 2026-09-29 in math.PR).
Categorie arXiv: Information Theory (cs.IT) ; Probability (math.PR).
Pagina del lavoro: https://arxiv.org/abs/2609.34570 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T23:02:49.398Z dalla pagina https://arxiv.org/catchup/math.PR/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).