Metraipolis › archive › dc_2e30513e668b

Composing Flow-Matching Energies with Known Physics: Generation, OOD Detection, and Inversion on PDE Fields — arXiv:2608.18004

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.18004
License (as archived)
CC0-1.0
Archived
2026-10-18T14:48:47.394Z
SHA-256 of the archived text
bf53fef3a89ae057e60de1704d84cd428c64af3d50b2be6f125a9c58e9a82fa8
Stable URL of this page
https://metraipolis.com/documento/dc_2e30513e668b

How to cite

Composing Flow-Matching Energies with Known Physics: Generation, OOD Detection, and Inversion on PDE Fields — arXiv:2608.18004 — arXiv (en), https://arxiv.org/abs/2608.18004 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2e30513e668b (Metraipolis archive dc_2e30513e668b, sha256 bf53fef3a89ae057e60de1704d84cd428c64af3d50b2be6f125a9c58e9a82fa8)
BibTeX
@misc{dc2e30513e668b,
  title = {Composing Flow-Matching Energies with Known Physics: Generation, OOD Detection, and Inversion on PDE Fields — arXiv:2608.18004},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.18004},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2e30513e668b; sha256 bf53fef3a89ae057e60de1704d84cd428c64af3d50b2be6f125a9c58e9a82fa8},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.18004. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Probabilistic modeling of physical fields benefits from both a data-driven prior and known physical structure such as the governing equations. Energy-based models (EBMs) are a natural fit since energies compose additively, which enables augmenting physics information during inference. However, EBMs have been difficult to train and sample from due to the intractable partition function. We show in this work that flow matching models with a potential-induced velocity yield an explicit scalar energy at all transport times, whose gradient is exactly the converted learned score and which recovers the marginal negative log-density at the population optimum. The time-dependent energy functions are obtained purely from the matching regression objective on an independent linear Gaussian interpolation, without a variational form or additional MCMC steps, and the sampling retains the flow ODE. Access to the energy function from a trained model serves three roles: energy-corrected data generation, energy as a scoring function for out-of-distribution (OOD) detection, and energy compositional posterior sampling for inverse problems. In particular, we show the explicit energy permits general MCMC samplers in the predictor-corrector sampling framework, reducing PDE residual and spectral distance compared to the flow ODE baseline. Furthermore, we demonstrate utilizing the data energy and physics-based energy (e.g., PDE residuals) as complementary mechanisms to improve detection accuracy for OOD tasks. In addition, we explore the connection to MCMC-based inference for inverse problems by composing the energy with a quadratic observational likelihood that yields a posterior energy, used as an explicitly chosen family of inference-time targets.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-19 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG) ; Computational Physics (physics.comp-ph).
Pagina del lavoro: https://arxiv.org/abs/2608.18004 — 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 2026-10-18T14:47:59.423Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-19?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).