mlsanityData to 7 Oct 2026

Practical Lossless Compression with Latent Variables using Bits Back Coding

arXiv 1901.04866 ↗First posted 15 Jan 2019cs.LG cs.AI cs.ITcited by 85

Not on the map. Why?

Abstract (arXiv)

Deep latent variable models have seen recent success in many data domains. Lossless compression is an application of these models which, despite having the potential to be highly useful, has yet to be implemented in a practical manner. We present `Bits Back with ANS' (BB-ANS), a scheme to perform lossless compression with latent variable models at a near optimal rate. We demonstrate this scheme by using it to compress the MNIST dataset with a variational auto-encoder model (VAE), achieving compression rates superior to standard methods with only a simple VAE. Given that the scheme is highly amenable to parallelization, we conclude that with a sufficiently high quality generative model this scheme could be used to achieve substantial improvements in compression rate with acceptable running time. We make our implementation available open source at https://github.com/bits-back/bits-back .

Key facts. Cited by 85 papers in the map (data through 7 Oct 2026). First posted on arXiv 15 Jan 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 23; 2022: 21; 2023: 9; 2024: 18; 2025: 9; 2026: 5.

85 papers.

Sort:

By area:

  1. 2021Variational Diffusion Modelscited by 1,145
  2. 2021Maximum Likelihood Training of Score-Based Diffusion Modelscited by 670
  3. 2023Language Modeling Is Compressioncited by 225
  4. 2021Autoregressive Diffusion Modelscited by 208
  5. 2024Image and Video Tokenization with Binary Spherical Quantizationcited by 110
  6. 2024GaussianImage: 1000 FPS Image Representation and Compression by 2D Gaussian Splattingcited by 97
  7. 2022An Introduction to Neural Data Compressioncited by 78
  8. 2023Bayesian Flow Networkscited by 62
  9. 2021Hierarchical VAEs Know What They Don't Knowcited by 58
  10. 2024Deep Generative Models through the Lens of the Manifold Hypothesis: A Survey and New Connectionscited by 47
  11. 2021On the Out-of-distribution Generalization of Probabilistic Image Modellingcited by 32
  12. 2022Lossy Image Compression with Quantized Hierarchical VAEscited by 32
38 more
  1. 2021Algorithms for the Communication of Samplescited by 31
  2. 2022Diagnosing and Fixing Manifold Overfitting in Deep Generative Modelscited by 28
  3. 2021iVPF: Numerical Invertible Volume Preserving Flow for Efficient Lossless Compressioncited by 27
  4. 2024Idempotence and Perceptual Image Compressioncited by 27
  5. 2022A Fast Transformer-based General-Purpose Lossless Compressorcited by 26
  6. 2021iFlow: Numerically Invertible Flows for Efficient Lossless Compression via a Uniform Codercited by 25
  7. 2023Computationally-Efficient Neural Image Compression with Shallow Decoderscited by 22
  8. 2024What is the Relationship between Tensor Factorizations and Circuits (and How Can We Exploit it)?cited by 22
  9. 2022Deep Lossy Plus Residual Coding for Lossless and Near-lossless Image Compressioncited by 21
  10. 2021Lossless Compression with Probabilistic Circuitscited by 20
  11. 2021Improving Lossless Compression Rates via Monte Carlo Bits-Back Codingcited by 19
  12. 2022Sparse Probabilistic Circuits via Pruning and Growingcited by 17
  13. 2021Learning Scalable ℓ_∞-constrained Near-lossless Image Compression via Joint Lossy Image and Residual Compressioncited by 16
  14. 2021Entropic Issues in Likelihood-Based OOD Detectioncited by 16
  15. 2021Neural Distributed Source Codingcited by 13
  16. 2021Towards Empirical Sandwich Bounds on the Rate-Distortion Functioncited by 13
  17. 2024Improving Probabilistic Diffusion Models With Optimal Diagonal Covariance Matchingcited by 13
  18. 2024Compression via Pre-trained Transformers: A Study on Byte-Level Multimodal Datacited by 13
  19. 2022Gacs-Korner Common Information Variational Autoencodercited by 12
  20. 2021Exploring the Latent Space of Autoencoders with Interventional Assayscited by 10
  21. 2021Partition and Code: learning how to compress graphscited by 10
  22. 2022Understanding Entropy Coding With Asymmetric Numeral Systems (ANS): a Statistician's Perspectivecited by 10
  23. 2022Generalization Gap in Amortized Inferencecited by 10
  24. 2021IB-DRR: Incremental Learning with Information-Back Discrete Representation Replaycited by 9
  25. 2024Scaling Continuous Latent Variable Models as Probabilistic Integral Circuitscited by 9
  26. 2023Probabilistic Integral Circuitscited by 8
  27. 2021Pragmatic Image Compression for Human-in-the-Loop Decision-Makingcited by 7
  28. 2023Approximating Human-Like Few-shot Learning with GPT-based Compressioncited by 7
  29. 2021Lossless compression with state space models using bits back codingcited by 6
  30. 2022Improving VAE-based Representation Learningcited by 6
  31. 2023Conditional Perceptual Quality Preserving Image Compressioncited by 6
  32. 2024GroupedMixer: An Entropy Model with Group-wise Token-Mixers for Learned Image Compressioncited by 6
  33. 2024CALLIC: Content Adaptive Learning for Lossless Image Compressioncited by 6
  34. 2022PILC: Practical Image Lossless Compression with an End-to-end GPU Oriented Neural Frameworkcited by 5
  35. 2022Few-Shot Non-Parametric Learning with Deep Latent Variable Modelcited by 5
  36. 2022Multi-Sample Training for Neural Image Compressioncited by 5
  37. 2024Learning Lossless Compression for High Bit-Depth Volumetric Medical Imagecited by 5
  38. 2021Lossless Compression with Latent Variable Modelscited by 4

50 most cited of 85 All 85 (JSON)