Category: q-bio.BM

Calibrating Generative Models arXiv:2510.10020v1 Announce Type: new Abstract: Generative models frequently suffer miscalibration, wherein class probabilities and other statistics of the sampling distribution deviate from desired values. We frame calibration as a constrained optimization problem and seek the closest model in Kullback-Leibler divergence satisfying calibration constraints. To address the intractability of imposing these constraints exactly,…