clm_b5f19b5cOur best results are obtained by training on a weighted variational bound designed according to a novel connection between diffusion probabilistic models and denoising score matching with Langevin dynamics, and … (excerpt)
arXiv 2006.11239 · cs.LG stat.ML
Read on arXiv · arXiv non-exclusive license
Claims were extracted automatically by reducer-1 on 2026-11-12. The paper's license does not allow republishing it, so long claims are shortened to a quotation. Read the full text on arXiv.
clm_b5f19b5cOur best results are obtained by training on a weighted variational bound designed according to a novel connection between diffusion probabilistic models and denoising score matching with Langevin dynamics, and … (excerpt)
res_bc57ae80On the unconditional CIFAR10 dataset, we obtain an Inception score of 9.46 and a state-of-the-art FID score of 3.17.
clm_61b8ee80We show that diffusion models actually are capable of generating high quality samples, sometimes better than the published results on other types of generative models (Section 4).
res_e61578ffIn addition, we show that a certain parameterization of diffusion models reveals an equivalence with denoising score matching over multiple noise levels during training and with annealed Langevin dynamics during … (excerpt)
res_99cef8f5Despite their sample quality, our models do not have competitive log likelihoods compared to other likelihood-based models (our models do, however, have log likelihoods better than the large estimates annealed … (excerpt)
clm_3195eae1We present a more refined analysis of this phenomenon in the language of lossy compression, and we show that the sampling procedure of diffusion models is a type of progressive … (excerpt)
res_edec9063Still, while our lossless codelengths are better than the large estimates reported for energy based models and score matching using annealed importance sampling [ 11], they are not competitive with … (excerpt)
clm_ba65de94We have presented high quality image samples using diffusion models, and we have found connections among diffusion models and variational inference for training Markov chains, denoising score matching and annealed … (excerpt)
res_45b3025eOur model architecture, forward process definition, and prior differ from NCSN [55, 56] in subtle but important ways that improve sample quality, and, notably, we directly train our sampler as … (excerpt)
Record your result in the Mearc app on your own machine, then use Publish this result with this paper's id (2006.11239) and the claim id shown next to the claim. Mearc creates a file that holds only what you choose to publish. Add it to the public claim data by pull request; a maintainer other than you reviews it before it counts.