Metraipolis › archive › dc_72067f9d5e02

Beyond Blackwell: Constrained Data Processing Inequalities — arXiv:2611.00510

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.00510
License (as archived)
CC0-1.0
Archived
2026-11-03T18:35:16.191Z
SHA-256 of the archived text
267ced9888c822474bfe0d791c615c7235301ae3ec4b7210808c0d0f6e9b7023
Stable URL of this page
https://metraipolis.com/documento/dc_72067f9d5e02

How to cite

Beyond Blackwell: Constrained Data Processing Inequalities — arXiv:2611.00510 — arXiv (en), https://arxiv.org/abs/2611.00510 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_72067f9d5e02 (Metraipolis archive dc_72067f9d5e02, sha256 267ced9888c822474bfe0d791c615c7235301ae3ec4b7210808c0d0f6e9b7023)
BibTeX
@misc{dc72067f9d5e02,
  title = {Beyond Blackwell: Constrained Data Processing Inequalities — arXiv:2611.00510},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.00510},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_72067f9d5e02; sha256 267ced9888c822474bfe0d791c615c7235301ae3ec4b7210808c0d0f6e9b7023},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00510. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We study the comparison of statistical experiments from a decision-theoretic standpoint, working with Markov transitions as basis-free linear maps on dual spaces. Our starting observation is that the data-processing inequality, that adding noise to an experiment cannot lower its Bayes risk, is the functoriality of fibrewise minimisation over a presheaf of decision rules: the rules available after an experiment form a presheaf, garbling acts on it by precomposition, and a risk functional is a natural transformation from it to the ordered reals. The argument refers to neither probabilities nor expected values, and it survives replacing the decision presheaf by a sub-presheaf of admissible rules. Any constraint imposed on the strategy that a rule induces fairness, unbiasedness, is automatically of this form, and so yields a data-processing inequality with no counterpart in the unconstrained Blackwell theory. Our main result is their quantitative companion. For constraints closed under post-processing we define a constrained deficiency and prove a constrained randomization theorem: one experiment dominates another on every admissible decision problem exactly when the constrained deficiency is small. The classical theorem is the case of no constraint, where the identity is itself an admissible rule; in general it is not, and the constrained deficiency is an optimisation over the coarsenings of an experiment that render it compliant. Specialising to equalized odds, we exhibit a pair of experiments that unconstrained Bayes risk identifies at a given loss and prior but that the constrained risk separates, giving a one-line certificate of Blackwell-incomparability. We work throughout with finite sets.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2611.00510 — 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 2026-11-03T18:12:54.430Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).