Metraipolis › archive › dc_45eea06fc2d4

Discretization and Statistical Consistency of Functional Flow Matching — arXiv:2608.04531

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.04531
License (as archived)
CC0-1.0
Archived
2026-10-31T11:34:50.753Z
SHA-256 of the archived text
81160ee19f960b5b2136f1a22218c053b7a11ada6f30acf9f5514ae34c9dad0b
Stable URL of this page
https://metraipolis.com/documento/dc_45eea06fc2d4

How to cite

Discretization and Statistical Consistency of Functional Flow Matching — arXiv:2608.04531 — arXiv (en), https://arxiv.org/abs/2608.04531 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_45eea06fc2d4 (Metraipolis archive dc_45eea06fc2d4, sha256 81160ee19f960b5b2136f1a22218c053b7a11ada6f30acf9f5514ae34c9dad0b)
BibTeX
@misc{dc45eea06fc2d4,
  title = {Discretization and Statistical Consistency of Functional Flow Matching — arXiv:2608.04531},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.04531},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_45eea06fc2d4; sha256 81160ee19f960b5b2136f1a22218c053b7a11ada6f30acf9f5514ae34c9dad0b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.04531. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Functional flow matching learns to generate random functions, such as velocity fields or solutions of partial differential equations, by continuously transforming a simple probability distribution into a target distribution. In practice, however, training and sampling use only finitely many grid values or coefficients. Does refining these observations recover the intended function-space model, and how do observation, learning, and numerical errors affect the generated distribution? We address these questions by first proving that the velocity targets used for training converge in mean square when the finite reconstructions converge to the underlying functions and remain uniformly bounded. The observations need not be nested: each refinement may replace earlier sensor locations. We also give quantitative bounds for orthogonal projections and extend the result to point observations under suitable regularity and reconstruction assumptions. We then bound the discrepancy between the generated and target distributions in Wasserstein distance, separating observation, learning, numerical, and endpoint errors without requiring uniqueness of the population finite-dimensional dynamics. For a normalized quadrature neural operator representing the learned velocity field, we establish stability and learning bounds with constants independent of the number of sensors. Under fixed model dimension and boundedness assumptions, the statistical excess risk decreases at an inverse-sample-size rate, up to logarithmic factors. A Gaussian example combines these estimates into an explicit sampling-error rate.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-06 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG) ; Probability (math.PR); Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2608.04531 — 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 2026-10-31T11:24:48.785Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-06?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).