Timezone: »

 
Poster
Bit-Swap: Recursive Bits-Back Coding for Lossless Compression with Hierarchical Latent Variables
Friso Kingma · Pieter Abbeel · Jonathan Ho

Thu Jun 13 06:30 PM -- 09:00 PM (PDT) @ Pacific Ballroom #6
in Posters Thu »

The bits-back argument suggests that latent variable models can be turned into lossless compression schemes. Translating the bits-back argument into efficient and practical lossless compression schemes for general latent variable models, however, is still an open problem. Bits-Back with Asymmetric Numeral Systems (BB-ANS), recently proposed by Townsend et al,. 2019, makes bits-back coding practically feasible for latent variable models with one latent layer, but it is inefficient for hierarchical latent variable models. In this paper we propose Bit-Swap, a new compression scheme that generalizes BB-ANS and achieves strictly better compression rates for hierarchical latent variable models with Markov chain structure. Through experiments we verify that Bit-Swap results in lossless compression rates that are empirically superior to existing techniques.

Keywords: Deep Generative Models · Generative Models · Information Theory and Estimation · Unsupervised Learning

Author Information

Friso Kingma (UC Berkeley)
Pieter Abbeel (OpenAI / UC Berkeley)
Jonathan Ho (UC Berkeley)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors