Skip to content
DraconiticResearch
Search Sources API
185,139 studies31 sourcesUpdated 30 min ago
PreprintCC BY 4.0arXiv

Distribution-Dependent Improvements of McDiarmid's Inequality via Rényi Divergence

  • Amedeo Roberto Esposito
  • Adrien Vandenbroucque
  • Michael Gastpar
Open at sourcePDFDOICite

Abstract

We investigate whether Rényi divergence can sharpen McDiarmid's inequality and its distribution-dependent refinement induced by KL divergence. Starting from Marton's transportation proof, we show that its transport inequality fails in general when KL divergence is replaced by Rényi divergence of order 0<α<1. For sums of independent bounded random variables, however, the additivity of Rényi divergence allows us to adapt the argument and derive concentration bounds. For Bernoulli sums, these bounds strictly improve on the distribution-dependent bound induced by KL divergence over a range of deviation thresholds. We also establish a distribution-dependent refinement of Gilardoni's inequality relating total variation to Rényi divergence, providing explicit constants for our general concentration bounds.

Related

  1. A One-Sided McDiarmid-Type Inequality for Heavy Tails via Reverse KL Tensorization
    Hanuka Eshima, Amedeo Roberto Esposito, Andrea Paudice
    arXivPreprintCC BY 4.0Full textProbabilityStatisticsarXiv
  2. A Generalized McDiarmid Inequality: Sample Reuse and Non-Uniform Unbounded Differences
    Jeremiah Birrell
    arXivPreprintarXiv licenceFull textStatisticsarXiv
  3. Optimal Non-Homogeneous Improvements of the Anisotropic Hardy Inequality
    Giuseppina di Blasio, Giovanni Pisante, Georgios Psaradakis
    arXivPreprintarXiv licenceFull textAnalysis & PDEsarXiv
  4. Divergence-Minimizing Distribution Matching for Parallel Channels and Channels with Memory
    Francesca Diedolo, Gerhard Kramer
    arXivPreprintarXiv licenceFull textGeneral mathematicsarXiv
  5. On Minimum Divergence for Distribution Reconstruction
    Justin Bec, Thomas Le Corre, Aurélien Garivier
    HALPreprintCC BY 4.0Full textStatisticsHALarXiv

Cite

BibTeXRIS
BibTeX
@misc{esposito2026distributiondependent,
  title = {{Distribution-Dependent Improvements of McDiarmid's Inequality via Rényi Divergence}},
  author = {Amedeo Roberto Esposito and Adrien Vandenbroucque and Michael Gastpar},
  howpublished = {arXiv},
  year = {2026},
  month = oct,
  doi = {10.48550/arxiv.2610.17736},
  eprint = {2610.17736},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.17736},
  note = {CC BY 4.0},
}
RIS
TY  - UNPB
TI  - Distribution-Dependent Improvements of McDiarmid's Inequality via Rényi Divergence
AU  - Amedeo Roberto Esposito
AU  - Adrien Vandenbroucque
AU  - Michael Gastpar
PY  - 2026
DA  - 2026/10/13
PB  - arXiv
DO  - 10.48550/arxiv.2610.17736
UR  - https://arxiv.org/abs/2610.17736
AB  - We investigate whether Rényi divergence can sharpen McDiarmid's inequality and its distribution-dependent refinement induced by KL divergence. Starting from Marton's transportation proof, we show that its transport inequality fails in general when KL divergence is replaced by Rényi divergence of order 0<α<1. For sums of independent bounded random variables, however, the additivity of Rényi divergence allows us to adapt the argument and derive concentration bounds. For Bernoulli sums, these bounds strictly improve on the distribution-dependent bound induced by KL divergence over a range of deviation thresholds. We also establish a distribution-dependent refinement of Gilardoni's inequality relating total variation to Rényi divergence, providing explicit constants for our general concentration bounds.
ER  -