Metraipolis › archive › dc_2aee1abc2a66

Principled MAP estimation for inverse problems: bridging the gap between convergence and performance — arXiv:2609.37529

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.37529
License (as archived)
CC0-1.0
Archived
2026-10-07T17:32:58.217Z
SHA-256 of the archived text
2252a4374b39ec27d691e3e2c300a6a6ed73e8dc2844adcd0d5e5e15a1238bf4
Stable URL of this page
https://metraipolis.com/documento/dc_2aee1abc2a66

How to cite

Principled MAP estimation for inverse problems: bridging the gap between convergence and performance — arXiv:2609.37529 — arXiv (en), https://arxiv.org/abs/2609.37529 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2aee1abc2a66 (Metraipolis archive dc_2aee1abc2a66, sha256 2252a4374b39ec27d691e3e2c300a6a6ed73e8dc2844adcd0d5e5e15a1238bf4)
BibTeX
@misc{dc2aee1abc2a66,
  title = {Principled MAP estimation for inverse problems: bridging the gap between convergence and performance — arXiv:2609.37529},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.37529},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2aee1abc2a66; sha256 2252a4374b39ec27d691e3e2c300a6a6ed73e8dc2844adcd0d5e5e15a1238bf4},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.37529. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Pretrained denoisers provide a powerful way to incorporate image priors into restoration algorithms. Plug-and-Play and RED approaches exploit fixed-noise-level denoisers within first-order optimization schemes, with convergence guarantees, but often struggle to achieve high-quality reconstruction on severely ill-posed inverse problems. In contrast, recent state-of-the-art approaches leverage denoisers derived from flow- or diffusion-based generative models and evaluate them along a sequence of decreasing noise levels. While these methods achieve strong empirical performance, their convergence theory remains limited. In this paper, we bridge this gap by specifically designing an algorithm that combines denoisers at decreasing noise levels with a schedule tailored to ensure convergence. From a Bayesian perspective, we prove that our method converges to a $\textit{Maximum a Posteriori}$ (MAP) estimate, under suitable assumptions. Subsequently, we apply our method to various ill-posed inverse problems and show that it surpasses convergent methods while competing with state-of-the-art empirical ones.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.LG).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.37529 — 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 2026-10-07T16:59:48.557Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).