##Statistics Seminar##\\ Department of Mathematics and Statistics ^ **DATE:**|Thursday, November 2, 2023 | ^ **TIME:**|1:15pm -- 2:15pm | ^ **LOCATION:**|WH 100E | ^ **SPEAKER:**|Geran Zhao, Binghamton University | ^ **TITLE:**|Denoising Diffusion Probabilistic Models | \\ **Abstract** The paper presents high quality image synthesis results using diffusion probabilistic models, a class of latent variable models inspired by considerations from nonequilibrium thermodynamics. The best results are obtained in this paper 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 our models naturally admit a progressive lossy decompression scheme that can be interpreted as a generalization of autoregressive decoding. On the unconditional CIFAR10 dataset, we obtain an Inception score of 9.46 and a state-of-the-art FID score of 3.17. On 256x256 LSUN, we obtain sample quality similar to ProgressiveGAN.