Variational Diffusion Models. (arXiv:2107.00630v6 [cs.LG] UPDATED)

Diffusion-based generative models have demonstrated a capacity for
perceptually impressive synthesis, but can they also be great likelihood-based
models? We answer this in the affirmative, and introduce a family of
diffusion-based generative models that obtain state-of-the-art likelihoods on
standard image density estimation benchmarks. Unlike other diffusion-based
models, our method allows for efficient optimization of the noise schedule
jointly with the rest of the model. We show that the variational lower bound
(VLB) simplifies to a remarkably short expression in terms …

art arxiv benchmarks capacity data diffusion diffusion models family generative generative models image likelihood noise optimization rest signal standard state synthesis terms understanding