Wavelet Score-Based Generative Modeling. (arXiv:2208.05003v1 [cs.LG])

Score-based generative models (SGMs) synthesize new data samples from
Gaussian white noise by running a time-reversed Stochastic Differential
Equation (SDE) whose drift coefficient depends on some probabilistic score. The
discretization of such SDEs typically requires a large number of time steps and
hence a high computational cost. This is because of ill-conditioning properties
of the score that we analyze mathematically. We show that SGMs can be
considerably accelerated, by factorizing the data distribution into a product
of conditional probabilities of …

arxiv lg modeling