Improving Adversarial Energy-Based Model via Diffusion Process

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Geng, Cong, Han, Tian, Jiang, Peng-Tao, Zhang, Hao, Chen, Jinwei, Hauberg, Søren, Li, Bo
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916279917477888
author Geng, Cong
Han, Tian
Jiang, Peng-Tao
Zhang, Hao
Chen, Jinwei
Hauberg, Søren
Li, Bo
author_facet Geng, Cong
Han, Tian
Jiang, Peng-Tao
Zhang, Hao
Chen, Jinwei
Hauberg, Søren
Li, Bo
contents Generative models have shown strong generation ability while efficient likelihood estimation is less explored. Energy-based models~(EBMs) define a flexible energy function to parameterize unnormalized densities efficiently but are notorious for being difficult to train. Adversarial EBMs introduce a generator to form a minimax training game to avoid expensive MCMC sampling used in traditional EBMs, but a noticeable gap between adversarial EBMs and other strong generative models still exists. Inspired by diffusion-based models, we embedded EBMs into each denoising step to split a long-generated process into several smaller steps. Besides, we employ a symmetric Jeffrey divergence and introduce a variational posterior distribution for the generator's training to address the main challenges that exist in adversarial EBMs. Our experiments show significant improvement in generation compared to existing adversarial EBMs, while also providing a useful energy function for efficient density estimation.
format Preprint
id arxiv_https___arxiv_org_abs_2403_01666
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Improving Adversarial Energy-Based Model via Diffusion Process
Geng, Cong
Han, Tian
Jiang, Peng-Tao
Zhang, Hao
Chen, Jinwei
Hauberg, Søren
Li, Bo
Machine Learning
Computer Vision and Pattern Recognition
Generative models have shown strong generation ability while efficient likelihood estimation is less explored. Energy-based models~(EBMs) define a flexible energy function to parameterize unnormalized densities efficiently but are notorious for being difficult to train. Adversarial EBMs introduce a generator to form a minimax training game to avoid expensive MCMC sampling used in traditional EBMs, but a noticeable gap between adversarial EBMs and other strong generative models still exists. Inspired by diffusion-based models, we embedded EBMs into each denoising step to split a long-generated process into several smaller steps. Besides, we employ a symmetric Jeffrey divergence and introduce a variational posterior distribution for the generator's training to address the main challenges that exist in adversarial EBMs. Our experiments show significant improvement in generation compared to existing adversarial EBMs, while also providing a useful energy function for efficient density estimation.
title Improving Adversarial Energy-Based Model via Diffusion Process
topic Machine Learning
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2403.01666