Metraipolis › archive › dc_0e73edbb222b
Randomization Beyond Deterministic Adaptivity in Parallel Sampling — arXiv:2610.03335
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.03335
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T08:40:25.653Z
- SHA-256 of the archived text
eac81d9b0be099e4e71993db8db73a02551af7fbd13d3cbecf7ff3ec09072677- Stable URL of this page
https://metraipolis.com/documento/dc_0e73edbb222b
How to cite
Randomization Beyond Deterministic Adaptivity in Parallel Sampling — arXiv:2610.03335 — arXiv (en), https://arxiv.org/abs/2610.03335 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0e73edbb222b (Metraipolis archive dc_0e73edbb222b, sha256 eac81d9b0be099e4e71993db8db73a02551af7fbd13d3cbecf7ff3ec09072677)
BibTeX
@misc{dc0e73edbb222b,
title = {Randomization Beyond Deterministic Adaptivity in Parallel Sampling — arXiv:2610.03335},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.03335},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0e73edbb222b; sha256 eac81d9b0be099e4e71993db8db73a02551af7fbd13d3cbecf7ff3ec09072677},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.03335. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We study parallel samplers that reveal each coordinate once and draw the coordinates of each batch independently from their exact conditional marginals. Under the same sampling interface and a hard three-round cap, randomization can improve accuracy beyond every deterministic policy that adapts its batches to previously observed values. For an explicit full-support binary family, the optimal deterministic adaptive forward Kullback-Leibler divergence grows linearly with the dimension, while a uniform mixture of four fixed schedules has exponentially small divergence. Only two independent fair bits are needed to select the schedule. We determine the asymptotic additive constant in the deterministic optimum and show that its optimal total variation tends to one quarter. An outward-rounded finite-sum certificate establishes divergence separation at dimension 389. The mechanism combines an irreversible first-batch dependence loss with posterior concentration in the randomized components. A density-coverage lemma describes how their mixture restores the target. A complementary noisy-matching family exhibits a growing round gap for nonadaptive schedules, although uniform random coordinate order still has linear mixture error. These results concern known finite structures and exact conditional marginals. Tema degli esploratori: matematica e informatica teorica (retro-catalogo arXiv: annunci del 2026-10-05 in math.IT). Categorie arXiv: Information Theory (cs.IT). Pagina del lavoro: https://arxiv.org/abs/2610.03335 — 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 2026-10-06T08:19:47.055Z dalla pagina https://arxiv.org/catchup/math.IT/2026-10-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).