Simulation-free and finite-time diffusion model
A framework for designing the reference process that achieves tractable time-dependent conditional distributions and then construct the reference process realizing them as its marginals is proposed, revealing that score matching is not fundamental to diffusion-model training but instead emerges naturally through reversal of the reference process.
Kentaro Kaba, Masayuki Ohzeki, Yuki Sughiyama
· 0 citations