Metraipolis › archive › dc_df4a0218ae29

Kinetic Langevin Meets Split Gibbs: Accelerated Posterior Sampling for Imaging Inverse Problems with Diffusion Priors — arXiv:2610.10187

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.10187
License (as archived)
CC0-1.0
Archived
2026-10-08T12:37:23.474Z
SHA-256 of the archived text
cf1ab507a818bceff545b17b86a267ba43c566bd99f036f11537c6fb3e828b47
Stable URL of this page
https://metraipolis.com/documento/dc_df4a0218ae29

How to cite

Kinetic Langevin Meets Split Gibbs: Accelerated Posterior Sampling for Imaging Inverse Problems with Diffusion Priors — arXiv:2610.10187 — arXiv (en), https://arxiv.org/abs/2610.10187 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_df4a0218ae29 (Metraipolis archive dc_df4a0218ae29, sha256 cf1ab507a818bceff545b17b86a267ba43c566bd99f036f11537c6fb3e828b47)
BibTeX
@misc{dcdf4a0218ae29,
  title = {Kinetic Langevin Meets Split Gibbs: Accelerated Posterior Sampling for Imaging Inverse Problems with Diffusion Priors — arXiv:2610.10187},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.10187},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_df4a0218ae29; sha256 cf1ab507a818bceff545b17b86a267ba43c566bd99f036f11537c6fb3e828b47},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.10187. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Split Gibbs sampling (SGS) is a popular framework for posterior sampling in Bayesian imaging inverse problems. It decouples a Gaussian data-fidelity term from a complex prior through an auxiliary variable, so the data variable is updated exactly and only the prior-side conditional is hard to sample. Existing samplers treat this conditional in one of two ways. Plug-and-play SGS runs a multi-step diffusion denoiser at every iteration, which is expensive and lacks non-asymptotic guarantees. Langevin-within-SGS takes cheap overdamped Langevin steps but needs many iterations. We propose RED-KLwSGS, which keeps the exact Gaussian update for the data variable and updates the auxiliary variable with underdamped (kinetic) Langevin diffusions driven by a one-shot denoising score, at the same per-iteration cost as Langevin-within-SGS. We prove non-asymptotic Wasserstein-2 convergence in continuous and discrete time for strongly log-concave priors. We also introduce Joint-RED-KLwSGS, which applies kinetic Langevin diffusions to both variables. Experiments with Denoising diffusion probabilistic models as diffusion priors on FFHQ and ImageNet datasets show faster convergence and high-quality image reconstruction.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (stat.ML) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.10187 — 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 2026-10-08T12:14:15.450Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).