Lossless Compression with Bits-Back Coding (Paper Explained) скачать в хорошем качестве

Lossless Compression with Bits-Back Coding (Paper Explained)

Paper link: https://arxiv.org/abs/1901.04866 Abstract: 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 this https URL . Authors: James Townsend, Tom Bird, David Barber 00:00 - Introduction 01:10 - How does compression work? 08:00 - Compressing with latent variables 13:10 - Bits-back coding scheme (overview) 18:50 - Sampling from q(z | x) using random bits, and getting "bits-back" 27:30 - The ELBO optimizes the code length exactly 29:00 - Visual steps of bits-back coding Connect with me: Twitter:   / andreimargeloiu   LinkedIn:   / andreimargeloiu