mlsanityData to 7 Oct 2026

Lossless compression with state space models using bits back coding

arXiv 2103.10150 ↗First posted 18 Mar 2021cs.LG cs.AI cs.ITcited by 6

Not on the map. Why?

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.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 6 of its 17 references that are in the map. First posted on arXiv 18 Mar 2021.

Builds on

6 of 17 references.

References · 6

  1. 2016Composing graphical models with neural networks for structured representations and fast inferencecited by 113
  2. 2019Practical Lossless Compression with Latent Variables using Bits Back Codingcited by 85
  3. 2019Bit-Swap: Recursive Bits-Back Coding for Lossless Compression with Hierarchical Latent Variablescited by 51
  4. 2021Clockwork Variational Autoencoderscited by 40
  5. 2019HiLLoC: Lossless Image Compression with Hierarchical Latent Variable Modelscited by 36
  6. 2021Improving Lossless Compression Rates via Monte Carlo Bits-Back Codingcited by 19

Built on by

Cited by year

Citing papers per year: 2021: 2; 2022: 2; 2023: 1; 2024: 1.

6 papers.

  1. 2022An Introduction to Neural Data Compressioncited by 78
  2. 2021Lossless Compression with Latent Variable Modelscited by 4
  3. 2021Compressing Multisets with Large Alphabets using Bits-Back Codingcited by 4
  4. 2023Random Edge Coding: One-Shot Bits-Back Coding of Large Labeled Graphscited by 2
  5. 2022Latent Discretization for Continuous-time Sequence Compressioncited by 0
  6. 2024Efficient Compression of Sparse Accelerator Data Using Implicit Neural Representations and Importance Samplingcited by 0