Improving Lossless Compression Rates via Monte Carlo Bits-Back Coding

arXiv2102.11086MaRDI QIDQ6361281

Chris J. Maddison, James Townsend, Karen Ullrich, Ashish Khisti, Alireza Makhzani, Daniel Severo, Yangjun Ruan, Arnaud Doucet

Publication date: 22 February 2021

Abstract: 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.

Has companion code repository: https://github.com/ryoungj/mcbits

This page was built for publication: Improving Lossless Compression Rates via Monte Carlo Bits-Back Coding

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6361281)