Learning Energy-Based Models by Diffusion Recovery Likelihood

Ruiqi Gao, Yang Song, Ben Poole, Ying Nian Wu, Diederik P Kingma

Keywords: energy-based model, EBM, recovery likelihood, generative model, diffusion process, MCMC, Langevin dynamics, HMC

Abstract: While energy-based models (EBMs) exhibit a number of desirable properties, training and sampling on high-dimensional datasets remains challenging. Inspired by recent progress on diffusion probabilistic models, we present a diffusion recovery likelihood method to tractably learn and sample from a sequence of EBMs trained on increasingly noisy versions of a dataset. Each EBM is trained with recovery likelihood, which maximizes the conditional probability of the data at a certain noise level given their noisy versions at a higher noise level. Optimizing recovery likelihood is more tractable than marginal likelihood, as sampling from the conditional distributions is much easier than sampling from the marginal distributions. After training, synthesized images can be generated by the sampling process that initializes from Gaussian white noise distribution and progressively samples the conditional distributions at decreasingly lower noise levels. Our method generates high fidelity samples on various image datasets. On unconditional CIFAR-10 our method achieves FID 9.58 and inception score 8.30, superior to the majority of GANs. Moreover, we demonstrate that unlike previous work on EBMs, our long-run MCMC samples from the conditional distributions do not diverge and still represent realistic images, allowing us to accurately estimate the normalized density of data even for high-dimensional datasets. Our implementation is available at \url{https://github.com/ruiqigao/recovery_likelihood}.

One-sentence Summary: We present a diffusion recovery likelihood method to tractably learn and sample from a sequence of EBMs based on a diffusion process. High sample quality, stable long-run MCMC chains and good estimation of likelihood.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Code: [ ruiqigao/recovery_likelihood](https://github.com/ruiqigao/recovery_likelihood) + [ 1 community implementation](https://paperswithcode.com/paper/?openreview=v_1Soh8QUNc)

Data: [CIFAR-10](https://paperswithcode.com/dataset/cifar-10), [CelebA](https://paperswithcode.com/dataset/celeba), [LSUN](https://paperswithcode.com/dataset/lsun)

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:2012.08125/code)