Metraipolis › archive › dc_fbe82e148982

Neural Wasserstein Splines: Representation-Invariant Second-Order Priors for Trajectory Inference — arXiv:2610.19878

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.19878
License (as archived)
CC0-1.0
Archived
2026-10-15T14:18:46.168Z
SHA-256 of the archived text
eef8b97c28df406e85c1f747c4d36e4c20ca137afb2d13634e64c13be7999243
Stable URL of this page
https://metraipolis.com/documento/dc_fbe82e148982

How to cite

Neural Wasserstein Splines: Representation-Invariant Second-Order Priors for Trajectory Inference — arXiv:2610.19878 — arXiv (en), https://arxiv.org/abs/2610.19878 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fbe82e148982 (Metraipolis archive dc_fbe82e148982, sha256 eef8b97c28df406e85c1f747c4d36e4c20ca137afb2d13634e64c13be7999243)
BibTeX
@misc{dcfbe82e148982,
  title = {Neural Wasserstein Splines: Representation-Invariant Second-Order Priors for Trajectory Inference — arXiv:2610.19878},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.19878},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fbe82e148982; sha256 eef8b97c28df406e85c1f747c4d36e4c20ca137afb2d13634e64c13be7999243},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.19878. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Population dynamics are often observed only as unpaired snapshots, which leave the evolution between measurements underdetermined. Second-order regularization can constrain it, but a penalty on the accelerations of sampled particles is a prior on joint particle paths, and different particle representations of the same marginal curve can have different acceleration costs. We therefore introduce Neural Wasserstein Splines (NWSP), a sample-based method that learns a continuous population curve under a Wasserstein smoothness prior. A neural network maps latent variables to the control points of a cubic spline in time, so samples at any time come from the spline basis without numerical integration. We project the generator's velocity onto gradients of a finite dictionary of scalar potentials and differentiate this measure-dependent projection in time, obtaining a finite-dimensional surrogate for the intrinsic Wasserstein acceleration, trained jointly with distributional fit losses. For a fixed dictionary and ridge parameter, we prove that the population penalty depends only on the marginal curve and bound its sensitivity to moment-estimation errors. Learned potentials (NWSP-N) sharpen acceleration estimates. On various synthetic and single-cell benchmarks, NWSP is highly competitive with transport and flow-based methods, ranking in the top two in 11 of 16 settings. The penalty improves on an unregularized spline in 13 of 16 settings and, while competitive with a particle-acceleration penalty, adds provable representation invariance.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2610.19878 — 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 2026-10-15T13:53:35.664Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).