SOTAVerified

Lossless compression with state space models using bits back coding

2021-03-18ICLR Workshop Neural_Compression 2021Code Available0· sign in to hype

James Townsend, Iain Murray

Code Available — Be the first to reproduce this paper.

Reproduce

Code

Abstract

We generalize the 'bits back with ANS' method to time-series models with a latent Markov structure. This family of models includes hidden Markov models (HMMs), linear Gaussian state space models (LGSSMs) and many more. We provide experimental evidence that our method is effective for small scale models, and discuss its applicability to larger scale settings such as video compression.

Tasks

Reproductions