Recent Posts

We introduce three types of invertible convolutions: i) emerging convolutions for invertible zero-padded convolutions, ii) invertible periodic convolutions, and iii) stable and flexible 1 x 1 convolutions. convolutions

Publications

Media is generally stored digitally and is therefore discrete. Many successful deep distribution models in deep learning learn a …

Autoregressive models (ARMs) currently hold state-of-the-art performance in likelihood-based modeling of image and audio data. …

Normalizing Flows (NFs) are able to model complicated distributions p(y) with strong inter-dimensional correlations and high …

Lossless compression methods shorten the expected representation size of data without loss of information, using a statistical model. …

Generative flows are attractive because they admit exact likelihood optimization and efficient image synthesis. Recently, Kingma & …