Preprint
Jul 2026
From Atoms to Entropy: Optimal Noise Allocation for Diffusion Training in the Convex Regime
A general statistical framework for studying asymptotically optimal noise-level allocation in diffusion training and an idealized independent-learner regime, intended to model temporal specialization in neural networks are developed.
Luca Ambrogioni, Giulio Franzese, Alberto Foresti et al.
· 2 citations