Subspace Diffusion Generative Models. (arXiv:2205.01490v1 [cs.LG])

Web: http://arxiv.org/abs/2205.01490

Score-based models generate samples by mapping noise to data (and vice versa)
via a high-dimensional diffusion process. We question whether it is necessary
to run this entire process at high dimensionality and incur all the
inconveniences thereof. Instead, we restrict the diffusion via projections onto
subspaces as the data distribution evolves toward noise. When applied to
state-of-the-art models, our framework simultaneously improves sample quality
-- reaching an FID of 2.17 on unconditional CIFAR-10 -- and reduces the
computational cost of …

arxiv models