The data geometry of masking diffusion: Certified-optimal schedules via unmasking growth complexity
By Martin J. Wainwright · Paper · cs.LG
We study masking diffusion for discrete sampling and introduce a path-resolved measure of data geometry called the \emph{unmasking growth complexity} ({\textsf{UGC}\xspace}). Its local increments directly control Kullback--Leibler (KL) discretization error, yielding a unified ana