Probabilistic Auto-Encoder

We introduce the probabilistic auto-encoder (PAE), a generative model with a lower dimensional latent space that is based on an auto-encoder which is interpreted probabilistically after training using a normalizing flow. The PAE is fast and easy to train, achieves small reconstruction errors, high sample quality and good performance in downstream tasks. Compared to a VAE and its common variants, the PAE trains faster, reaches a lower reconstruction error and produces state of the art sample quality without requiring special tuning parameters or training procedures. We further demonstrate that the PAE is a powerful model for performing the downstream tasks of outlier detection and probabilistic image reconstruction: 1) We identify a PAE-based outlier detection metric which achieves state of the art results and outperforms other likelihood based estimators. 2) We perform high dimensional data inpainting and denoising with uncertainty quantification by means of posterior analysis in the PAE latent space. Most generative models are specifically tuned to excel in one or two applications. With the PAE we introduce an easy-to-train, simple, but at the same time powerful model that performs well and reliably in many tasks without requiring special fine-tuning or training procedures. We make all PAE codes publicly available.