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

This paper introduces a new method to build linear flows, by taking the exponential of a linear transformation. This linear …

Normalizing flows and variational autoencoders are powerful generative models that can represent complicated density functions. …

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 …