A New Look on Diffusion Times for Score-based Generative Models

Score-based diffusion models map noise into data using stochastic differential equations. While current practice advocates for a large $T$ to ensure closeness to steady state, a smaller value of $T$ should be preferred for a better approximation of the score-matching objective and computational efficiency. We conjecture, contrary to current belief and corroborated by numerical evidence, that the optimal diffusion times are smaller than current practice.