Instead, we propose to use noise contrastive estimation (NCE) to discriminatively learn the EBM through density ratio estimation between the latent prior density and latent posterior density.
To the best of our knowledge, denoising diffusion GAN is the first model that reduces sampling cost in diffusion models to an extent that allows them to be applied to real-world applications inexpensively.
Ranked #8 on Image Generation on CelebA-HQ 256x256
Unsupervised outlier detection, which predicts if a test sample is an outlier or not using only the information from unlabelled inlier data, is an important but challenging task.
Doing so allows us to study the density induced by the dynamics (if the dynamics are invertible), and connect with GANs by treating the dynamics as generator models, the initial values as latent variables and the loss as optimizing a critic defined by the very same energy that determines the generator through its gradient.
ControlVAE is a new variational autoencoder (VAE) framework that combines the automatic control theory with the basic VAE to stabilize the KL-divergence of VAE models to a specified value.
VAEBM captures the overall mode structure of the data distribution using a state-of-the-art VAE and it relies on its EBM component to explicitly exclude non-data-like regions from the model and refine the image samples.
Ranked #1 on Image Generation on Stacked MNIST
In this paper, we present a general method that can improve the sample quality of pre-trained likelihood based generative models.
An important application of generative modeling should be the ability to detect out-of-distribution (OOD) samples by setting a threshold on the likelihood.
Recently, Coordinate Descent (CD) with cyclic order was shown to be $O(n^2)$ times slower than randomized versions in the worst-case.