Timezone: »

Improving Lossless Compression Rates via Monte Carlo Bits-Back Coding
Yangjun Ruan · Karen Ullrich · Daniel Severo · James Townsend · Ashish Khisti · Arnaud Doucet · Alireza Makhzani · Chris Maddison

Wed Jul 21 09:00 AM -- 11:00 AM (PDT) @

Latent variable models have been successfully applied in lossless compression with the bits-back coding algorithm. However, bits-back suffers from an increase in the bitrate equal to the KL divergence between the approximate posterior and the true posterior. In this paper, we show how to remove this gap asymptotically by deriving bits-back coding algorithms from tighter variational bounds. The key idea is to exploit extended space representations of Monte Carlo estimators of the marginal likelihood. Naively applied, our schemes would require more initial bits than the standard bits-back coder, but we show how to drastically reduce this additional cost with couplings in the latent space. When parallel architectures can be exploited, our coders can achieve better rates than bits-back with little additional cost. We demonstrate improved lossless compression rates in a variety of settings, especially in out-of-distribution or sequential data compression.

Author Information

Yangjun Ruan (University of Toronto)
Karen Ullrich (FAIR)
Daniel Severo (University of Toronto)
James Townsend (UCL)
Ashish Khisti (Univ. of Toronto)
Arnaud Doucet (Oxford University)
Alireza Makhzani (University of Toronto)
Chris Maddison (University of Toronto)

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

More from the Same Authors