Metraipolis › archive › dc_a2832172cd7b
Noise, Denoise, Correct: MCMC Posterior Sampling with Diffusion Priors in Three Steps — arXiv:2610.09407
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.09407
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T11:56:37.603Z
- SHA-256 of the archived text
2f77375a5a0a164515ad839121086eaedf5c4ba6b8ed46399350ed6014adabab- Stable URL of this page
https://metraipolis.com/documento/dc_a2832172cd7b
How to cite
Noise, Denoise, Correct: MCMC Posterior Sampling with Diffusion Priors in Three Steps — arXiv:2610.09407 — arXiv (en), https://arxiv.org/abs/2610.09407 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a2832172cd7b (Metraipolis archive dc_a2832172cd7b, sha256 2f77375a5a0a164515ad839121086eaedf5c4ba6b8ed46399350ed6014adabab)
BibTeX
@misc{dca2832172cd7b,
title = {Noise, Denoise, Correct: MCMC Posterior Sampling with Diffusion Priors in Three Steps — arXiv:2610.09407},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.09407},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a2832172cd7b; sha256 2f77375a5a0a164515ad839121086eaedf5c4ba6b8ed46399350ed6014adabab},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.09407. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Pretrained diffusion models are powerful priors for inverse problems, but posterior sampling under nonlinear, non-differentiable forward models remain hard. We introduce diffusion waltz, an MCMC method using SDEdit-style noising-denoising as a proposal, corrected via Metropolis-Hastings for exact posterior sampling without prior evaluation. We further propose injecting observations into the proposal while preserving exactness, using a gradient-free ensemble Kalman update. On a non-differentiable Navier-Stokes initial condition recovery task, diffusion waltz outperforms existing baselines across different noise and nonlinearity regimes. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2610.09407 — 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 2026-10-08T10:50:37.682Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).