A proxy model with adaptive constrained optimization enables non-adversarial minimization of the Jeffreys divergence, producing more stable and accurate distribution fitting than MLE or GANs especially in low-data regimes.
Estimation of non-normalized statistical models by score matching.Journal of Ma- chine Learning Research, 6(24):695–709
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Adaptive Symmetrization of the KL Divergence
A proxy model with adaptive constrained optimization enables non-adversarial minimization of the Jeffreys divergence, producing more stable and accurate distribution fitting than MLE or GANs especially in low-data regimes.