Learning Energy-Based Models by Cooperative Diffusion Recovery Likelihood

arXiv:2309.05153v3 Announce Type: replace-cross
Abstract: Training energy-based models (EBMs) on high-dimensional data can be both challenging and time-consuming, and there exists a noticeable gap in sample quality between EBMs and other generative frameworks like GANs and diffusion models. To close this gap, inspired by the recent efforts of learning EBMs by maximizing diffusion recovery likelihood (DRL), we propose cooperative diffusion recovery likelihood (CDRL), an effective approach to tractably learn and sample from a series of EBMs defined on increasingly noisy …

abstract arxiv cs.lg data diffusion diffusion models energy frameworks gans gap generative likelihood quality recovery sample stat.ml training type