Metraipolis › archive › dc_568018f71d04

Wasserstein de-initialization for Markov chains — arXiv:2610.10234

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.10234
License (as archived)
CC0-1.0
Archived
2026-10-08T12:42:47.744Z
SHA-256 of the archived text
9e49cc8eff2f6620bf8baab8aa95a5a30d82d5d0b280c5ab4a659f172bc4eb97
Stable URL of this page
https://metraipolis.com/documento/dc_568018f71d04

How to cite

Wasserstein de-initialization for Markov chains — arXiv:2610.10234 — arXiv (en), https://arxiv.org/abs/2610.10234 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_568018f71d04 (Metraipolis archive dc_568018f71d04, sha256 9e49cc8eff2f6620bf8baab8aa95a5a30d82d5d0b280c5ab4a659f172bc4eb97)
BibTeX
@misc{dc568018f71d04,
  title = {Wasserstein de-initialization for Markov chains — arXiv:2610.10234},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.10234},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_568018f71d04; sha256 9e49cc8eff2f6620bf8baab8aa95a5a30d82d5d0b280c5ab4a659f172bc4eb97},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.10234. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

This article generalizes the de-initialization framework, proposed by (Roberts and Rosenthal, 2001) for total variation distance, to Wasserstein distances. In essence, de-initialization captures the phenomenon that in the presence of certain structural features, the convergence behaviour of a Markov chain can be reduced to that of a "simpler" stochastic process. Our results allow to measure this in terms of a general Wasserstein distance. We apply them to analyse the Wasserstein convergence behaviour of Gibbs sampling, linchpin variable sampling and slice sampling.

Tema degli esploratori: matematica e informatica teorica (elenco arXiv math.ST, nuovi lavori del giorno).
Categorie arXiv: Probability (math.PR) ; Statistics Theory (math.ST).
Pagina del lavoro: https://arxiv.org/abs/2610.10234 — 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 2026-10-08T12:16:15.208Z dalla pagina https://arxiv.org/list/math.ST/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).