Targeted tweaks to DDPMs produce competitive likelihoods and high-quality samples, with learned reverse variances enabling 10x faster sampling and predictable scaling with compute.
The model trained with the linear schedule learns more slowly, but does not overfit as quickly
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2021 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
Improved Denoising Diffusion Probabilistic Models
Targeted tweaks to DDPMs produce competitive likelihoods and high-quality samples, with learned reverse variances enabling 10x faster sampling and predictable scaling with compute.