Integer Discrete Flows and Lossless Compression
Emiel Hoogeboom · Jorn Peters · Rianne van den Berg · Max Welling

Wed Dec 11th 05:00 -- 07:00 PM @ East Exhibition Hall B + C #144

Lossless compression methods shorten the expected representation size of data without loss of information, using a statistical model. Flow-based models are attractive in this setting because they admit exact likelihood optimization, which is equivalent to minimizing the expected number of bits per message. However, conventional flows assume continuous data, which may lead to reconstruction errors when quantized for compression. For that reason, we introduce a flow-based generative model for ordinal discrete data called Integer Discrete Flow (IDF): a bijective integer map that can learn rich transformations on high-dimensional data. As building blocks for IDFs, we introduce a flexible transformation layer called integer discrete coupling. Our experiments show that IDFs are competitive with other flow-based generative models. Furthermore, we demonstrate that IDF based compression achieves state-of-the-art lossless compression rates on CIFAR10, ImageNet32, and ImageNet64. To the best of our knowledge, this is the first lossless compression method that uses invertible neural networks.

Author Information

Emiel Hoogeboom (University of Amsterdam)
Jorn Peters (University of Amsterdam)
Rianne van den Berg (Google Brain)
Max Welling (University of Amsterdam / Qualcomm AI Research)

More from the Same Authors