# Lossless Compression with Latent Variable Models

Source: [Lossless Compression with Latent Variable Models](<https://www.sota2.com/research/paper/68fa580b1e209131ce9aabc3>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T15:05:34.824Z

Authors: James Townsend

Published: 2021-04-21T14:03:05.000Z

## Abstract

We develop a simple and elegant method for lossless compression using latent variable models, which we call 'bits back with asymmetric numeral systems' (BB-ANS). The method involves interleaving encode and decode steps, and achieves an optimal rate when compressing batches of data. We demonstrate it firstly on the MNIST test set, showing that state-of-the-art lossless compression is possible using a small variational autoencoder (VAE) model. We then make use of a novel empirical insight, that fully convolutional generative models, trained on small images, are able to generalize to images of arbitrary size, and extend BB-ANS to hierarchical latent variable models, enabling state-of-the-art lossless compression of full-size colour images from the ImageNet dataset. We describe 'Craystack', a modular software framework which we have developed for rapid prototyping of compression using deep generative models.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2104.10544>)

[PDF](<https://arxiv.org/pdf/2104.10544.pdf>)