Metraipolis › archive › dc_6f35dc2362ee

Learning to Replace MCMC in Split-Gibbs Diffusion Posterior Sampling via Deep Unfolding — arXiv:2609.30539

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.30539
License (as archived)
CC0-1.0
Archived
2026-10-08T02:19:08.922Z
SHA-256 of the archived text
07effc3590a25ce2b53fbe80bdaf3b397fae66ec7ee2781164178258dfd9016e
Stable URL of this page
https://metraipolis.com/documento/dc_6f35dc2362ee

How to cite

Learning to Replace MCMC in Split-Gibbs Diffusion Posterior Sampling via Deep Unfolding — arXiv:2609.30539 — arXiv (en), https://arxiv.org/abs/2609.30539 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6f35dc2362ee (Metraipolis archive dc_6f35dc2362ee, sha256 07effc3590a25ce2b53fbe80bdaf3b397fae66ec7ee2781164178258dfd9016e)
BibTeX
@misc{dc6f35dc2362ee,
  title = {Learning to Replace MCMC in Split-Gibbs Diffusion Posterior Sampling via Deep Unfolding — arXiv:2609.30539},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.30539},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6f35dc2362ee; sha256 07effc3590a25ce2b53fbe80bdaf3b397fae66ec7ee2781164178258dfd9016e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.30539. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Split Gibbs sampling enables diffusion posterior inference for general nonlinear inverse problems by decoupling prior and likelihood computations, allowing a pretrained diffusion prior to be reused across measurement models. However, its likelihood update often relies on iterative MCMC, which can hinder parallelization, require algorithm-specific tuning, and incur substantial computational cost. In this work, we propose a learning-based framework to replace this MCMC step by reformulating both Gibbs updates as Gaussian denoising problems and implementing them through ODE diffusion. The prior step reuses a pretrained denoiser, while the likelihood denoiser exploits known likelihood structure through a lightweight deep-unfolded network. Experiments on nonlinear phase retrieval demonstrate the effectiveness of the proposed method as an alternative to MCMC-based split Gibbs at lower likelihood-update cost.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-28 in cs.LG).
Categorie arXiv: Signal Processing (eess.SP) ; Machine Learning (cs.LG); Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2609.30539 — 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 2026-10-08T01:43:06.783Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).