Skip to main content
Search

# Predictor-Corrector Sampling

1 related articles

Subscribe to updates
  1. arXiv

    A correction step for flow matching: Marginal Matching reaches FID 3.45 on CIFAR-10 at 41 function evaluations

    Flow matching models turn noise into samples along an ordinary differential equation, but the learned flow field is imperfect and the sampling trajectory drifts from the true data distribution. Marginal Matching inserts a separately trained corrector during inference that pulls samples toward the marginal distribution obtained by integrating the same flow field backward, backed by an analysis showing the correction lowers a bound on Wasserstein distance. On CIFAR-10, with OT-CFM as the base model and 10-step RK4 sampling (40 function evaluations), one correction step gives FID 3.45, against 4.34 for the uncorrected OT-CFM RK4 baseline.

You’re all caught up