mlsanityData to 7 Oct 2026

Compression with Flows via Local Bits-Back Coding

arXiv 1905.08500 ↗First posted 21 May 2019cs.LG cs.IT math.ITcited by 34

Not on the map. Why?

Abstract (arXiv)

Likelihood-based generative models are the backbones of lossless compression due to the guaranteed existence of codes with lengths close to negative log likelihood. However, there is no guaranteed existence of computationally efficient codes that achieve these lengths, and coding algorithms must be hand-tailored to specific types of generative models to ensure computational efficiency. Such coding algorithms are known for autoregressive models and variational autoencoders, but not for general types of flow models. To fill in this gap, we introduce local bits-back coding, a new compression technique for flow models. We present efficient algorithms that instantiate our technique for many popular types of flows, and we demonstrate that our algorithms closely achieve theoretical codelengths for state-of-the-art flow models on high-dimensional data.

Key facts. Cited by 34 papers in the map (data through 7 Oct 2026). First posted on arXiv 21 May 2019.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 15; 2022: 8; 2023: 0; 2024: 6; 2025: 5.

34 papers.

Sort:

By area:

  1. 2021Variational Diffusion Modelscited by 1,145
  2. 2021Maximum Likelihood Training of Score-Based Diffusion Modelscited by 670
  3. 2021Autoregressive Diffusion Modelscited by 208
  4. 2022An Introduction to Neural Data Compressioncited by 78
  5. 2024Diffusion Models, Image Super-Resolution And Everything: A Surveycited by 63
  6. 2021On the Out-of-distribution Generalization of Probabilistic Image Modellingcited by 32
  7. 2022Diagnosing and Fixing Manifold Overfitting in Deep Generative Modelscited by 28
  8. 2021iVPF: Numerical Invertible Volume Preserving Flow for Efficient Lossless Compressioncited by 27
  9. 2021iFlow: Numerically Invertible Flows for Efficient Lossless Compression via a Uniform Codercited by 25
  10. 2022Deep Lossy Plus Residual Coding for Lossless and Near-lossless Image Compressioncited by 21
  11. 2021Lossless Compression with Probabilistic Circuitscited by 20
  12. 2021Towards Empirical Sandwich Bounds on the Rate-Distortion Functioncited by 13
22 more
  1. 2021Partition and Code: learning how to compress graphscited by 10
  2. 2021Insights from Generative Modeling for Neural Video Compressioncited by 9
  3. 2024CALLIC: Content Adaptive Learning for Lossless Image Compressioncited by 6
  4. 2021Lossless Image Compression Using a Multi-Scale Progressive Statistical Modelcited by 5
  5. 2022PILC: Practical Image Lossless Compression with an End-to-end GPU Oriented Neural Frameworkcited by 5
  6. 2024Understanding Likelihood of Normalizing Flow and Image Complexity through the Lens of Out-of-Distribution Detectioncited by 5
  7. 2021Lossless Compression with Latent Variable Modelscited by 4
  8. 2022Split Hierarchical Variational Compressioncited by 4
  9. 2022Fast Lossless Neural Compression with Integer-Only Discrete Flowscited by 4
  10. 2021Learning Non-linear Wavelet Transformation via Normalizing Flowcited by 3
  11. 2024Test-time adaptation for image compression with distribution regularizationcited by 3
  12. 2021Discrete Denoising Flowscited by 2
  13. 2024Wavelet-Like Transform-Based Technology in Response to the Call for Proposals on Neural Network-Based Image Codingcited by 2
  14. 2025Likelihood Training of Cascaded Diffusion Models via Hierarchical Volume-preserving Mapscited by 2
  15. 2025LVPNet: A Latent-variable-based Prediction-driven End-to-end Framework for Lossless Compression of Medical Imagescited by 2
  16. 2022Extreme-scale Talking-Face Video Upsampling with Audio-Visual Priorscited by 1
  17. 2025SEEC: Segmentation-Assisted Multi-Entropy Models for Learned Lossless Image Compressioncited by 1
  18. 2021OSOA: One-Shot Online Adaptation of Deep Generative Models for Lossless Compressioncited by 0
  19. 2022Multi-Scale Architectures Matter: On the Adversarial Robustness of Flow-based Lossless Compressioncited by 0
  20. 2024FLLIC: Functionally Lossless Image Compressioncited by 0
  21. 2025Deep Robust Reversible Watermarkingcited by 0
  22. 2025The Algorithmic Regulatorcited by 0