Poster

Moment Matching Denoising Gibbs Sampling

Mingtian Zhang · Alex Hawkins-Hooker · Brooks Paige · David Barber

Great Hall & Hall B1+B2 (level 1) #1206
[ ]
Tue 12 Dec 8:45 a.m. PST — 10:45 a.m. PST

Abstract:

Energy-Based Models (EBMs) offer a versatile framework for modelling complex data distributions. However, training and sampling from EBMs continue to pose significant challenges. The widely-used Denoising Score Matching (DSM) method for scalable EBM training suffers from inconsistency issues, causing the energy model to learn a noisy data distribution. In this work, we propose an efficient sampling framework: (pseudo)-Gibbs sampling with moment matching, which enables effective sampling from the underlying clean model when given a noisy model that has been well-trained via DSM. We explore the benefits of our approach compared to related methods and demonstrate how to scale the method to high-dimensional datasets.

Chat is not available.