Metraipolis › archive › dc_e6fd10622dbd

Probabilistic Geodesic Flow Matching on Location-Scale Families — arXiv:2609.34613

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.34613
License (as archived)
CC0-1.0
Archived
2026-10-07T22:40:33.071Z
SHA-256 of the archived text
70c154e95cc79aa2521a7e9d87802da90065ab7d1ebad36f7459ca4654f346b2
Stable URL of this page
https://metraipolis.com/documento/dc_e6fd10622dbd

How to cite

Probabilistic Geodesic Flow Matching on Location-Scale Families — arXiv:2609.34613 — arXiv (en), https://arxiv.org/abs/2609.34613 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e6fd10622dbd (Metraipolis archive dc_e6fd10622dbd, sha256 70c154e95cc79aa2521a7e9d87802da90065ab7d1ebad36f7459ca4654f346b2)
BibTeX
@misc{dce6fd10622dbd,
  title = {Probabilistic Geodesic Flow Matching on Location-Scale Families — arXiv:2609.34613},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.34613},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e6fd10622dbd; sha256 70c154e95cc79aa2521a7e9d87802da90065ab7d1ebad36f7459ca4654f346b2},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.34613. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Flow matching (FM) has recently emerged as a promising framework for generative modeling due to its conceptual simplicity and strong empirical performance. In FM, samples are transported along a vector field parameterized by a neural network, inducing a probability path that evolves from a simple noise distribution to the target data distribution, governed by an ordinary differential equation (ODE). However, existing FM approaches predominantly rely on probability paths derived from optimal transport (OT) between Gaussian distributions, which may be suboptimal for capturing complex data with inhomogeneous structures such as heavy tail or sharp contrast. In this work, we generalize FM to the broader class of location-scale families for handling data inhomogeneity and introduce a novel class of probability paths defined as geodesics on the manifold of probability distributions. We name this approach probabilistic geodesic flow matching to distinguish it from prior geodesic (Riemannian) FM methods defined in input space. We argue that Euclidean OT-based paths are not necessarily optimal in probability space and may limit modeling flexibility. Through synthetic benchmarks and scientific datasets at different scales, we demonstrate that the proposed method more effectively captures complex distributions, leading to improved or comparable performance compared with SOTA geometry-motivated generative models.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.LG).
Categorie arXiv: Machine Learning (stat.ML) ; Machine Learning (cs.LG); Probability (math.PR).
Pagina del lavoro: https://arxiv.org/abs/2609.34613 — 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 2026-10-07T22:14:28.838Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).