Skip to main content
Search

# Isthmus Sampling

1 related articles

Subscribe to updates
  1. arXiv

    One-step flow samplers lose their uncertainty: Isthmus rewires only the time sampler and brings brain-MRI calibration back to multi-step levels

    When one-step flow maps serve as posterior samplers, the spread of their samples is the uncertainty they are meant to carry, yet the standard one-step sampler loses that spread and decorrelates from the 64-step samples of the same network. Isthmus spreads training time pairs along the whole edge of the time triangle that joins the one-step pair to the diagonal, so the one-step map's error is bounded by the self-consistency residual. On brain MRI, one-step calibration returns to 0.96 and correlation with multi-step samples to 0.93, and the agreement holds when training is extended to three times its length.

You’re all caught up