Metraipolis › archive › dc_46163ac29ea7

Local Geometric Mixing via Dobrushin Contraction with Applications to Diffusion Path Monte Carlo and the Proximal Sampler — arXiv:2609.28338

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.28338
License (as archived)
CC0-1.0
Archived
2026-10-08T10:58:24.980Z
SHA-256 of the archived text
005a3ba246b0c998a113ec1a019012fe330d720e6a3b5f22090f9dec2b71b424
Stable URL of this page
https://metraipolis.com/documento/dc_46163ac29ea7

How to cite

Local Geometric Mixing via Dobrushin Contraction with Applications to Diffusion Path Monte Carlo and the Proximal Sampler — arXiv:2609.28338 — arXiv (en), https://arxiv.org/abs/2609.28338 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_46163ac29ea7 (Metraipolis archive dc_46163ac29ea7, sha256 005a3ba246b0c998a113ec1a019012fe330d720e6a3b5f22090f9dec2b71b424)
BibTeX
@misc{dc46163ac29ea7,
  title = {Local Geometric Mixing via Dobrushin Contraction with Applications to Diffusion Path Monte Carlo and the Proximal Sampler — arXiv:2609.28338},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.28338},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_46163ac29ea7; sha256 005a3ba246b0c998a113ec1a019012fe330d720e6a3b5f22090f9dec2b71b424},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.28338. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Local geometric mixing localizes geometric mixing by requiring geometric convergence to equilibrium in total variation only over finitely many transitions. It accommodates local convergence rates and captures rapid local equilibration, even when global mixing is much slower. We establish and discuss local geometric mixing bounds through Dobrushin contraction. We then apply this approach to Diffusion Path Monte Carlo, a recently proposed Markov chain Monte Carlo method, aimed at leveraging advances in score-based modeling, whose ideal transitions coincide with those of the Proximal Sampler. Our analysis covers both the ideal method and its implementable Metropolis-adjusted counterpart, providing mixing guarantees under minimal assumptions. For the ideal method, these guarantees complement recent spectral gap estimates, which we develop into mixing time bounds.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-24 in cs.LG).
Categorie arXiv: Probability (math.PR) ; Machine Learning (cs.LG); Computation (stat.CO); Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2609.28338 — 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 2026-10-08T10:06:16.845Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).