Hitchhiker's guide on the relation of Energy-Based Models with other generative models, sampling and statistical physics: a comprehensive review

TL;DR

This comprehensive review explains how Energy-Based Models relate to other generative models, sampling methods, and statistical physics, aiming to unify diverse perspectives for physicists and machine learning researchers.

Contribution

It provides a detailed synthesis of EBMs, their connections to other models, sampling techniques, and recent training advancements, bridging gaps between physics and machine learning communities.

Findings

Clarifies the relationship between EBMs and other generative models

Highlights the role of MCMC and energy functions in sampling

Summarizes recent training methodologies for EBMs

Abstract

Energy-Based Models have emerged as a powerful framework in the realm of generative modeling, offering a unique perspective that aligns closely with principles of statistical mechanics. This review aims to provide physicists with a comprehensive understanding of EBMs, delineating their connection to other generative models such as Generative Adversarial Networks, Variational Autoencoders, and Normalizing Flows. We explore the sampling techniques crucial for EBMs, including Markov Chain Monte Carlo (MCMC) methods, and draw parallels between EBM concepts and statistical mechanics, highlighting the significance of energy functions and partition functions. Furthermore, we delve into recent training methodologies for EBMs, covering recent advancements and their implications for enhanced model performance and efficiency. This review is designed to clarify the often complex interconnections between these models, which can be challenging due to the diverse communities working on the topic.