Metraipolis › archive › dc_b8f4540db209

Model-Aware Schedules Improve Generation via Fiberwise Optimal Transport — arXiv:2609.11842

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.11842
License (as archived)
CC0-1.0
Archived
2026-10-16T05:27:18.127Z
SHA-256 of the archived text
6429c4f9a5fed737558f09e9bc46e48d17aeae863cf4cd9615f5f759f34c6e1a
Stable URL of this page
https://metraipolis.com/documento/dc_b8f4540db209

How to cite

Model-Aware Schedules Improve Generation via Fiberwise Optimal Transport — arXiv:2609.11842 — arXiv (en), https://arxiv.org/abs/2609.11842 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b8f4540db209 (Metraipolis archive dc_b8f4540db209, sha256 6429c4f9a5fed737558f09e9bc46e48d17aeae863cf4cd9615f5f759f34c6e1a)
BibTeX
@misc{dcb8f4540db209,
  title = {Model-Aware Schedules Improve Generation via Fiberwise Optimal Transport — arXiv:2609.11842},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.11842},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b8f4540db209; sha256 6429c4f9a5fed737558f09e9bc46e48d17aeae863cf4cd9615f5f759f34c6e1a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.11842. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Diffusion and flow-matching schedules control the signal and noise coefficients that mix data and noise along affine probability paths. Minimizing a kinetic action defined on coefficient paths, motivated by optimal transport, helps explain strong baselines but remains model-agnostic and ignores prediction error. Here we introduce a model-aware schedule construction based on fiberwise optimal transport. At a fixed time and state on the probability path, compatible signal/noise decompositions form an affine fiber. We define a fiberwise prediction risk by averaging optimal-transport costs between the true and predictor-induced decompositions within these fibers. On a fixed coefficient curve, combining this risk with coefficient-path kinetic action yields a closed-form optimal time allocation. This construction extends to general linear prediction targets, and the risk profile can be estimated from an early baseline checkpoint. We evaluate DDPMs and flow matching across prediction targets, training configurations, risk-estimation checkpoints, datasets, and architectures. Our model-aware schedules consistently outperform strong baselines, including a 38.6% relative FID reduction for flow matching on CIFAR-10 at 16 function evaluations. Each model-agnostic kinetic baseline determines its own kinetic reference coordinate. In these coordinates, fiberwise-risk profiles from independently trained models in different settings align closely after normalization to unit area. The resulting schedule deformations used in training also align, suggesting empirical universality across the evaluated models and settings. Pretrained-checkpoint diagnostics extend this normalized-risk agreement to larger conditional latent diffusion and 2-RF models. A frozen analytic allocation template retains most of the model-aware improvement without further risk estimation or model-specific fitting.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-11 in cs.AI).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.11842 — 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 2026-10-16T05:17:52.203Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).