# Lossless compression with state space models using bits back coding

arXiv: https://arxiv.org/abs/2103.10150 · HTML: https://mlsanity.com/paper/2103.10150/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 17 references that are in the map.
- First posted on arXiv 18 Mar 2021.

## Builds on (most cited first, 6 of 6)

- [Composing graphical models with neural networks for structured representations and fast inference](https://mlsanity.com/paper/1603.06277/) (2016)
- [Practical Lossless Compression with Latent Variables using Bits Back Coding](https://mlsanity.com/paper/1901.04866/) (2019)
- [Bit-Swap: Recursive Bits-Back Coding for Lossless Compression with Hierarchical Latent Variables](https://mlsanity.com/paper/1905.06845/) (2019)
- [Clockwork Variational Autoencoders](https://mlsanity.com/paper/2102.09532/) (2021)
- [HiLLoC: Lossless Image Compression with Hierarchical Latent Variable Models](https://mlsanity.com/paper/1912.09953/) (2019)
- [Improving Lossless Compression Rates via Monte Carlo Bits-Back Coding](https://mlsanity.com/paper/2102.11086/) (2021)

## Built on by (most cited first, 6 of 6)

- [An Introduction to Neural Data Compression](https://mlsanity.com/paper/2202.06533/) (2022)
- [Lossless Compression with Latent Variable Models](https://mlsanity.com/paper/2104.10544/) (2021)
- [Compressing Multisets with Large Alphabets using Bits-Back Coding](https://mlsanity.com/paper/2107.09202/) (2021)
- [Random Edge Coding: One-Shot Bits-Back Coding of Large Labeled Graphs](https://mlsanity.com/paper/2305.09705/) (2023)
- [Latent Discretization for Continuous-time Sequence Compression](https://mlsanity.com/paper/2212.13659/) (2022)
- [Efficient Compression of Sparse Accelerator Data Using Implicit Neural Representations and Importance Sampling](https://mlsanity.com/paper/2412.01754/) (2024)

## Abstract (arXiv)

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.