Early stopping plus normalizing flow initialization extends diffusion models to any target distribution with proven KL convergence, and a hybrid flow-SGM pipeline captures heavy tails without tail-specific assumptions.
p∞ in blue, pT in orange, pθ in green, real data in red
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Generalizing Score-based generative models for Heavy-tailed Distributions
Early stopping plus normalizing flow initialization extends diffusion models to any target distribution with proven KL convergence, and a hybrid flow-SGM pipeline captures heavy tails without tail-specific assumptions.