LGAIITMLMar 18, 2021

Lossless compression with state space models using bits back coding

arXiv:2103.10150v39 citations
Originality Synthesis-oriented
AI Analysis

This work addresses compression efficiency for time-series data, but it appears incremental as it extends an existing method to a broader model family.

The authors tackled lossless compression for time-series models with latent Markov structures by generalizing bits back coding with ANS, and demonstrated its effectiveness on small-scale models while discussing potential for larger applications like video compression.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes