Generative Modeling by Estimating Gradients of the Data Distribution

12 Jul 2019Yang SongStefano Ermon

We introduce a new generative model where samples are produced via Langevin dynamics using gradients of the data distribution estimated with score matching. Because gradients might be ill-defined when the data resides on low-dimensional manifolds, we perturb the data with different levels of Gaussian noise and jointly estimate the corresponding scores, i.e., the vector fields of gradients of the perturbed data distribution for all noise levels... (read more)

PDF Abstract

Evaluation results from the paper

Task Dataset Model Metric name Metric value Global rank Compare
Image Generation CIFAR-10 NCSN Inception score 8.91 # 1
Image Generation CIFAR-10 NCSN FID 25.32 # 7