Model-Aware Schedules Improve Generation via Fiberwise Optimal Transport
Researchers introduce model-aware diffusion schedules via fiberwise optimal transport, cutting flow-matching FID on CIFAR-10 by 38.6% at 16 function evaluations.
The paper proposes constructing diffusion and flow-matching sampling schedules from a fiberwise prediction risk defined via optimal transport, combined with coefficient-path kinetic action, yielding a closed-form time allocation. Across DDPM and flow-matching experiments spanning targets, datasets, and architectures, the schedules beat model-agnostic baselines, including a 38.6% relative FID reduction for flow matching on CIFAR-10 at 16 function evaluations. Normalized fiberwise-risk profiles from independently trained models align closely, suggesting empirical universality, and a frozen analytic allocation template retains most of the gains.
- Fiberwise optimal-transport risk enables model-aware schedule construction for diffusion and flow matching.
- 38.6% relative FID reduction on CIFAR-10 flow matching at 16 function evaluations.
- Risk profiles from independently trained models align after normalization, hinting at universality.
- Pretrained-checkpoint diagnostics extend agreement to larger conditional latent diffusion and 2-RF models.
- Tags
- diffusion-modelsflow-matchinggenerative-modelsoptimal-transportsampling-schedulestraining-techniques
- Products
- DDPMflow matching
- AI models
- CIFAR-10
From the original article
1 min read at arxiv.orgDiffusion 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.
By Luyi Jia · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.