Practical Lossless Compression with Latent Variables using Bits Back Coding
This work addresses the challenge of making lossless compression practical for data storage and transmission, though it is incremental as it builds on existing latent variable models and coding schemes.
The paper tackles the problem of implementing practical lossless compression using deep latent variable models, presenting Bits Back with ANS (BB-ANS) to achieve near-optimal compression rates, demonstrated by compressing the MNIST dataset with a variational auto-encoder to achieve superior rates compared to standard methods.
Deep latent variable models have seen recent success in many data domains. Lossless compression is an application of these models which, despite having the potential to be highly useful, has yet to be implemented in a practical manner. We present `Bits Back with ANS' (BB-ANS), a scheme to perform lossless compression with latent variable models at a near optimal rate. We demonstrate this scheme by using it to compress the MNIST dataset with a variational auto-encoder model (VAE), achieving compression rates superior to standard methods with only a simple VAE. Given that the scheme is highly amenable to parallelization, we conclude that with a sufficiently high quality generative model this scheme could be used to achieve substantial improvements in compression rate with acceptable running time. We make our implementation available open source at https://github.com/bits-back/bits-back .