Derives the conditional score exactly from an unconditional score via affine maps for linear inverse problems in infinite dimensions, shifting computation to offline training.
Posteriorsamplesofsourcegalaxiesinstronggravitationallenseswithscore-based priors.CoRR, abs/2211.03812
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
fields
stat.ML 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
MIRA is a new analytic score for conditional distribution accuracy derived from equal probability mass assignment, enabling Bayesian model comparison via direct posterior validation.
citing papers explorer
-
An Unconditional Representation of the Conditional Score in Infinite-Dimensional Linear Inverse Problems
Derives the conditional score exactly from an unconditional score via affine maps for linear inverse problems in infinite dimensions, shifting computation to offline training.
-
MIRA: A Score for Conditional Distribution Accuracy and Model Comparison
MIRA is a new analytic score for conditional distribution accuracy derived from equal probability mass assignment, enabling Bayesian model comparison via direct posterior validation.