Improving Adversarial Energy-Based Model via Diffusion Process

arXiv:2403.01666v1 Announce Type: new
Abstract: 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 …

abstract adversarial arxiv cs.cv cs.lg diffusion energy form function game generative generative models generator likelihood minimax process train training type via