Skip to content
DraconiticResearch
Search Sources API
197,788 studies31 sourcesUpdated 14 min ago
PreprintarXiv licencearXiv

Wasserstein de-initialization for Markov chains

  • Mareike Hasenpflug
Open at sourcePDFDOICite

Abstract

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.

Related

  1. Bernstein’s inequalities for general Markov chains
    Bai Jiang, Qiang Sun, Jianqing Fan A B
    Annales de l Institut Henri Poincaré Probabilités et StatistiquesPeer-reviewedLicence not statedFull text40 citedStatisticsOpenAlex
  2. Dimension-free Convergence Rate in Sliced Wasserstein Distance for Empirical Measures of Markov Processes
    Feng-Yu Wang
    arXivPreprintCC0Full textProbabilityarXiv
  3. Global central limit theorems for Markov chains
    Christophe Cuny, Michael Lin
    Stochastic Processes and their ApplicationsPeer-reviewedCC BY 4.0Full text1 citedMathematical physicsHAL
  4. Global Central Limit Theorems for Markov chains with normal transition operator
    Christophe Cuny, Michael Lin
    HALPreprintCC BY-NC-ND 4.0Full textProbabilityHALarXiv
  5. Markov chains arising in the study of random matrices over pro-finite rings
    Nikita Lvov
    arXivPreprintCC BY 4.0Full textAlgebra & number theoryProbabilityarXiv

Cite

BibTeXRIS
BibTeX
@misc{hasenpflug2026wasserstein,
  title = {{Wasserstein de-initialization for Markov chains}},
  author = {Mareike Hasenpflug},
  howpublished = {arXiv},
  year = {2026},
  month = oct,
  doi = {10.48550/arxiv.2610.10234},
  eprint = {2610.10234},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.10234},
}
RIS
TY  - UNPB
TI  - Wasserstein de-initialization for Markov chains
AU  - Mareike Hasenpflug
PY  - 2026
DA  - 2026/10/07
PB  - arXiv
DO  - 10.48550/arxiv.2610.10234
UR  - https://arxiv.org/abs/2610.10234
AB  - 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.
ER  -