LGMLJul 12, 2019

Generative Modeling by Estimating Gradients of the Data Distribution

arXiv:1907.05600v35559 citations
Originality Highly original
AI Analysis

It provides a flexible, non-adversarial generative modeling framework for image generation, representing a novel method rather than an incremental improvement.

The paper tackles generative modeling by estimating gradients of the data distribution using score matching and Langevin dynamics, achieving a state-of-the-art inception score of 8.87 on CIFAR-10 and producing samples comparable to GANs on MNIST and CelebA.

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 can be ill-defined and hard to estimate 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. For sampling, we propose an annealed Langevin dynamics where we use gradients corresponding to gradually decreasing noise levels as the sampling process gets closer to the data manifold. Our framework allows flexible model architectures, requires no sampling during training or the use of adversarial methods, and provides a learning objective that can be used for principled model comparisons. Our models produce samples comparable to GANs on MNIST, CelebA and CIFAR-10 datasets, achieving a new state-of-the-art inception score of 8.87 on CIFAR-10. Additionally, we demonstrate that our models learn effective representations via image inpainting experiments.

Code Implementations13 repos

Data from Papers with Code (CC-BY-SA-4.0)

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes