Moment Matching Denoising Gibbs Sampling
Mingtian Zhang, Alex Hawkins-Hooker, Brooks Paige, David Barber
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.
BibTeX
@inproceedings{
zhang2023moment,
title={Moment Matching Denoising Gibbs Sampling},
author={Mingtian Zhang and Alex Hawkins-Hooker and Brooks Paige and David Barber},
booktitle={Thirty-seventh Conference on Neural Information Processing Systems},
year={2023},
url={https://openreview.net/forum?id=NWrN6cMG2x}
}