Metraipolis › archive › dc_024cc6f4c054

Twist Flow for Inverse Problems — arXiv:2610.09281

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.09281
License (as archived)
CC0-1.0
Archived
2026-10-08T11:56:32.871Z
SHA-256 of the archived text
8dc4544db0352ffac3d2a930f2f995dc3d9ff448fcb0476205e0ea9ec0be95bf
Stable URL of this page
https://metraipolis.com/documento/dc_024cc6f4c054

How to cite

Twist Flow for Inverse Problems — arXiv:2610.09281 — arXiv (en), https://arxiv.org/abs/2610.09281 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_024cc6f4c054 (Metraipolis archive dc_024cc6f4c054, sha256 8dc4544db0352ffac3d2a930f2f995dc3d9ff448fcb0476205e0ea9ec0be95bf)
BibTeX
@misc{dc024cc6f4c054,
  title = {Twist Flow for Inverse Problems — arXiv:2610.09281},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.09281},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_024cc6f4c054; sha256 8dc4544db0352ffac3d2a930f2f995dc3d9ff448fcb0476205e0ea9ec0be95bf},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.09281. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

In Bayesian inverse problems, posterior sampling requires generating samples that are consistent with given observations while capturing the range of plausible solutions. Direct conditional generative models introduce latent noise to model this ambiguity, but paired inverse-problem training can still encourage an almost deterministic map from the observation to the target. As a result, generated samples may be observation-consistent while under-representing posterior variability, especially when the posterior is multimodal, leading to undercoverage, mode distortion, or artificial transitions between distinct feasible solutions. We propose joint twist-flow, an augmented flow-matching formulation that learns a continuous transport from the augmented source state $(z_x, y)$ to the augmented terminal state $(x, z_y)$. Here x is the target variable, $y$ is the observation, $z_x$ is the Gaussian reference coordinate for posterior sampling, and $z_y$ is a Gaussian likelihood-side coordinate associated with the observation branch. Under a Gaussian observation model, $z_y$ is motivated by the normalized observation residual associated with observation compatibility. Its role is not to replace uncertainty in $x$, but to couple generated samples of x to observation consistency, helping reduce likelihood-inconsistent variation while preserving variability in weakly constrained directions. We validate the method on low-dimensional inverse problems with reference posterior samples, where joint twist-flow better preserves multimodal posterior support than a direct conditional-flow baseline. We further evaluate the method on image restoration and seismic subsurface velocity-model inversion, showing increased posterior variability while maintaining observation consistency.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Geophysics (physics.geo-ph).
Pagina del lavoro: https://arxiv.org/abs/2610.09281 — 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 2026-10-08T10:50:37.674Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).