mlsanityData to 7 Oct 2026

Bit-Swap: Recursive Bits-Back Coding for Lossless Compression with Hierarchical Latent Variables

arXiv 1905.06845 ↗First posted 16 May 2019cs.LG cs.AI cs.ITcited by 51

Not on the map. Why?

Abstract (arXiv)

The bits-back argument suggests that latent variable models can be turned into lossless compression schemes. Translating the bits-back argument into efficient and practical lossless compression schemes for general latent variable models, however, is still an open problem. Bits-Back with Asymmetric Numeral Systems (BB-ANS), recently proposed by Townsend et al. (2019), makes bits-back coding practically feasible for latent variable models with one latent layer, but it is inefficient for hierarchical latent variable models. In this paper we propose Bit-Swap, a new compression scheme that generalizes BB-ANS and achieves strictly better compression rates for hierarchical latent variable models with Markov chain structure. Through experiments we verify that Bit-Swap results in lossless compression rates that are empirically superior to existing techniques. Our implementation is available at https://github.com/fhkingma/bitswap.

Key facts. Cited by 51 papers in the map (data through 7 Oct 2026). First posted on arXiv 16 May 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 16; 2022: 16; 2023: 7; 2024: 8; 2025: 3; 2026: 1.

51 papers.

Sort:

By area:

  1. 2021Variational Diffusion Modelscited by 1,145
  2. 2023Language Modeling Is Compressioncited by 225
  3. 2021On the Out-of-distribution Generalization of Probabilistic Image Modellingcited by 32
  4. 2022Lossy Image Compression with Quantized Hierarchical VAEscited by 32
  5. 2021iVPF: Numerical Invertible Volume Preserving Flow for Efficient Lossless Compressioncited by 27
  6. 2022A Fast Transformer-based General-Purpose Lossless Compressorcited by 26
  7. 2021iFlow: Numerically Invertible Flows for Efficient Lossless Compression via a Uniform Codercited by 25
  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
38 more
  1. 2021Learning Scalable ℓ_∞-constrained Near-lossless Image Compression via Joint Lossy Image and Residual Compressioncited by 16
  2. 2021Towards Empirical Sandwich Bounds on the Rate-Distortion Functioncited by 13
  3. 2024Compression via Pre-trained Transformers: A Study on Byte-Level Multimodal Datacited by 13
  4. 2021Partition and Code: learning how to compress graphscited by 10
  5. 2022Understanding Entropy Coding With Asymmetric Numeral Systems (ANS): a Statistician's Perspectivecited by 10
  6. 2022Generalization Gap in Amortized Inferencecited by 10
  7. 2021IB-DRR: Incremental Learning with Information-Back Discrete Representation Replaycited by 9
  8. 2024Scaling Continuous Latent Variable Models as Probabilistic Integral Circuitscited by 9
  9. 2023Probabilistic Integral Circuitscited by 8
  10. 2023Approximating Human-Like Few-shot Learning with GPT-based Compressioncited by 7
  11. 2021Lossless compression with state space models using bits back codingcited by 6
  12. 2024GroupedMixer: An Entropy Model with Group-wise Token-Mixers for Learned Image Compressioncited by 6
  13. 2024CALLIC: Content Adaptive Learning for Lossless Image Compressioncited by 6
  14. 2022PILC: Practical Image Lossless Compression with an End-to-end GPU Oriented Neural Frameworkcited by 5
  15. 2022Few-Shot Non-Parametric Learning with Deep Latent Variable Modelcited by 5
  16. 2021Lossless Compression with Latent Variable Modelscited by 4
  17. 2021Compressing Multisets with Large Alphabets using Bits-Back Codingcited by 4
  18. 2022Parallel Neural Local Lossless Compressioncited by 4
  19. 2022Practical Learned Lossless JPEG Recompression with Multi-Level Cross-Channel Entropy Model in the DCT Domaincited by 4
  20. 2022Split Hierarchical Variational Compressioncited by 4
  21. 2024Entropy Coding of Unordered Data Structurescited by 3
  22. 2025WISE: A Framework for Gigapixel Whole-Slide-Image Lossless Compressioncited by 3
  23. 2021Discrete Denoising Flowscited by 2
  24. 2023Random Edge Coding: One-Shot Bits-Back Coding of Large Labeled Graphscited by 2
  25. 2025LVPNet: A Latent-variable-based Prediction-driven End-to-end Framework for Lossless Compression of Medical Imagescited by 2
  26. 2023Learned Lossless Compression for JPEG via Frequency-Domain Predictioncited by 1
  27. 2023Inferring Population Dynamics in Macaque Cortexcited by 1
  28. 2024Learned Image Transmission with Hierarchical Variational Autoencodercited by 1
  29. 2025SEEC: Segmentation-Assisted Multi-Entropy Models for Learned Lossless Image Compressioncited by 1
  30. 2021Bayesian Attention Networks for Data Compressioncited by 0
  31. 2021OSOA: One-Shot Online Adaptation of Deep Generative Models for Lossless Compressioncited by 0
  32. 2022Learned Lossless JPEG Transcoding via Joint Lossy and Residual Compressioncited by 0
  33. 2022Multi-Scale Architectures Matter: On the Adversarial Robustness of Flow-based Lossless Compressioncited by 0
  34. 2022GOLLIC: Learning Global Context beyond Patches for Lossless High-Resolution Image Compressioncited by 0
  35. 2022Verified Reversible Programming for Verified Lossless Compressioncited by 0
  36. 2022Latent Discretization for Continuous-time Sequence Compressioncited by 0
  37. 2023Unified learning-based lossy and lossless JPEG recompressioncited by 0
  38. 2024FLLIC: Functionally Lossless Image Compressioncited by 0

50 most cited of 51 All 51 (JSON)