Metraipolis › archive › dc_da887bd14e52

FlowBudget: Training-Free Sampling-Budget Estimation for Flow Matching Models — arXiv:2610.20636

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.20636
License (as archived)
CC0-1.0
Archived
2026-10-16T10:19:51.807Z
SHA-256 of the archived text
f2c4d98b81ddb540ed8a9e9ffc3b592ea84cd670d429368d95ae023b8d7ab48e
Stable URL of this page
https://metraipolis.com/documento/dc_da887bd14e52

How to cite

FlowBudget: Training-Free Sampling-Budget Estimation for Flow Matching Models — arXiv:2610.20636 — arXiv (en), https://arxiv.org/abs/2610.20636 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_da887bd14e52 (Metraipolis archive dc_da887bd14e52, sha256 f2c4d98b81ddb540ed8a9e9ffc3b592ea84cd670d429368d95ae023b8d7ab48e)
BibTeX
@misc{dcda887bd14e52,
  title = {FlowBudget: Training-Free Sampling-Budget Estimation for Flow Matching Models — arXiv:2610.20636},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.20636},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_da887bd14e52; sha256 f2c4d98b81ddb540ed8a9e9ffc3b592ea84cd670d429368d95ae023b8d7ab48e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.20636. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Sampling from continuous flow-based generators such as flow matching models requires numerical ODE or SDE integration, making inference cost depend on the number of function evaluations (NFEs). In practice, the sampling budget is inherited from prior work or selected through expensive FID-versus-NFE sweeps, using FID to assess image-generation quality, requiring sample generation and evaluation at multiple budgets. This makes sampling-budget selection dependent on repeated empirical evaluation. We therefore ask a complementary question to solver design and timestep allocation: for a fixed pretrained model and solver, what numerical resolution is sufficient? We introduce FLOWBUDGET, a training-free estimator of solver-relative sampling complexity. Using simulation-free interpolation probes of the learned dynamics, FLOWBUDGET normalizes the leading one-step discretization error by the motion, estimates its coefficient from interpolation probes, and maps a numerical tolerance to a step budget using the solver order. We derive estimators for numerical solvers in flow~matching sampling, namely Euler and Heun for ODE sampling and additive-noise Euler--Maruyama for SDE sampling, and connect the ODE coefficients to terminal integration error. Experiments on SiT, FlowDCN and Rectified Flow models, spanning flow-model architectures and formulations, test whether FLOWBUDGET can estimate the NFE budget without generating samples at multiple budgets or performing an FID-versus-NFE sweep. The code is available at this https URL

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.20636 — 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 2026-10-16T08:48:02.636Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).