Metraipolis › archive › dc_b038d630f4e4
Exact Global MCMC with Denoising Diffusion — arXiv:2609.00279
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.00279
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T06:52:28.420Z
- SHA-256 of the archived text
de2b9c51f706fa672735a8c1680aa479a2966ca666a6db1830b6698456607950- Stable URL of this page
https://metraipolis.com/documento/dc_b038d630f4e4
How to cite
Exact Global MCMC with Denoising Diffusion — arXiv:2609.00279 — arXiv (en), https://arxiv.org/abs/2609.00279 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b038d630f4e4 (Metraipolis archive dc_b038d630f4e4, sha256 de2b9c51f706fa672735a8c1680aa479a2966ca666a6db1830b6698456607950)
BibTeX
@misc{dcb038d630f4e4,
title = {Exact Global MCMC with Denoising Diffusion — arXiv:2609.00279},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.00279},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b038d630f4e4; sha256 de2b9c51f706fa672735a8c1680aa479a2966ca666a6db1830b6698456607950},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.00279. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
This work shows that diffusion models learned with standard denoising loss can provide effective global MCMC proposals for complex high-dimensional target densities. The method is motivated by the observation that sequentially applying a forward and reverse diffusion process defines a Markov chain with a target stationary distribution for an ideal denoiser trained on samples of the target distribution. This observation can be made exact for any denoiser by applying a Metropolis-Hastings step whose acceptance ratio includes the density of the forward and reverse paths of a discrete time SDE approximation. We therefore propose to train denoising diffusion models on locally convergent MALA samples to learn global MCMC proposals. We call the composition of the global denoiser-based path sampler and a local MALA sampler Denoising Diffusion Monte Carlo (DDMC). Experiments show that DDMC can provide global proposals with high acceptance across a variety of complex target densities. Our results offer preliminary evidence that the established scaling behavior of standard diffusion training transfers directly to exact sampling from high-dimensional unnormalized densities. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-02 in cs.LG). Categorie arXiv: Machine Learning (stat.ML) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.00279 — 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 2026-10-17T06:41:55.878Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).