mlsanityData to 7 Oct 2026

Universally Quantized Neural Compression

arXiv 2006.09952 ↗First posted 17 Jun 2020stat.ML cs.CV cs.ITcited by 60

Not on the map. Why?

Abstract (arXiv)

A popular approach to learning encoders for lossy compression is to use additive uniform noise during training as a differentiable approximation to test-time quantization. We demonstrate that a uniform noise channel can also be implemented at test time using universal quantization (Ziv, 1985). This allows us to eliminate the mismatch between training and test phases while maintaining a completely differentiable loss function. Implementing the uniform noise channel is a special case of the more general problem of communicating a sample, which we prove is computationally hard if we do not make assumptions about its distribution. However, the uniform special case is efficient as well as easy to implement and thus of great interest from a practical point of view. Finally, we show that quantization can be obtained as a limiting case of a soft quantizer applied to the uniform noise channel, bridging compression with and without quantization.

Key facts. Cited by 60 papers in the map (data through 7 Oct 2026). First posted on arXiv 17 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 13; 2022: 8; 2023: 7; 2024: 13; 2025: 8; 2026: 11.

60 papers.

Sort:

By area:

  1. 2021A Survey of Quantization Methods for Efficient Neural Network Inferencecited by 798
  2. 2022Lossy Compression with Gaussian Diffusioncited by 87
  3. 2022An Introduction to Neural Data Compressioncited by 78
  4. 2023C3: High-performance and low-complexity neural compression from a single image or videocited by 54
  5. 2021Joint Global and Local Hierarchical Priors for Learned Image Compressioncited by 52
  6. 2021Lossy Compression for Lossless Predictioncited by 51
  7. 2022Lossy Image Compression with Quantized Hierarchical VAEscited by 32
  8. 2021Algorithms for the Communication of Samplescited by 31
  9. 2024NVRC: Neural Video Representation Compressioncited by 29
  10. 2021On the advantages of stochastic encoderscited by 28
  11. 2023Compression with Bayesian Implicit Neural Representationscited by 25
  12. 2024Spatial Decomposition and Temporal Fusion based Inter Prediction for Learned Video Compressioncited by 21
38 more
  1. 2021LVAC: Learned Volumetric Attribute Compression for Point Clouds using Coordinate Based Networkscited by 19
  2. 2023NVTC: Nonlinear Vector Transform Codingcited by 14
  3. 2021Towards Empirical Sandwich Bounds on the Rate-Distortion Functioncited by 13
  4. 2021Learning Cross-Scale Weighted Prediction for Efficient Neural Video Compressioncited by 12
  5. 2024Progressive Compression with Universally Quantized Diffusion Modelscited by 10
  6. 2023Compression with Exact Error Distribution for Federated Learningcited by 9
  7. 2025GIViC: Generative Implicit Video Compressioncited by 9
  8. 2024Universal Exact Compression of Differentially Private Mechanismscited by 8
  9. 2024Generalized Gaussian Model for Learned Image Compressioncited by 8
  10. 2021Versatile Learned Video Compressioncited by 7
  11. 2024QGen: On the Ability to Generalize in Quantization Aware Trainingcited by 7
  12. 2025Bridging the Gap between Gaussian Diffusion Models and Universal Quantization for Image Compressioncited by 7
  13. 2021Rate Distortion Characteristic Modeling for Neural Image Compressioncited by 6
  14. 2023Trading Information between Latents in Hierarchical Variational Autoencoderscited by 6
  15. 2024The Rate-Distortion-Perception Trade-off: The Role of Private Randomnesscited by 6
  16. 2022Multi-Sample Training for Neural Image Compressioncited by 5
  17. 2025Improving the Straight-Through Estimator with Zeroth-Order Informationcited by 5
  18. 2024Some Notes on the Sample Complexity of Approximate Channel Simulationcited by 4
  19. 2024STanH : Parametric Quantization for Variable Rate Learned Image Compressioncited by 4
  20. 2021Online Meta Adaptation for Variable-Rate Learned Image Compressioncited by 3
  21. 2026Enhanced Neural Video Representation Compression Across Extreme Complexity and Quality Scalescited by 3
  22. 2022Do Neural Networks Compress Manifolds Optimally?cited by 2
  23. 2024Exploration of Learned Lifting-Based Transform Structures for Fully Scalable and Accessible Wavelet-Like Image Compressioncited by 2
  24. 2024Wavelet-Like Transform-Based Technology in Response to the Call for Proposals on Neural Network-Based Image Codingcited by 2
  25. 2025Communication-Efficient and Privacy-Adaptable Mechanism for Federated Learningcited by 2
  26. 2025Optimal Neural Compressors for the Rate-Distortion-Perception Tradeoffcited by 2
  27. 2021Principal Bit Analysis: Autoencoding with Schur-Concave Losscited by 1
  28. 2022Leveraging progressive model and overfitting for efficient learned image compressioncited by 1
  29. 2024An Information-Theoretic Regularizer for Lossy Neural Image Compressioncited by 1
  30. 2025BiVM: Accurate Binarized Neural Network for Efficient Video Mattingcited by 1
  31. 2026Communication-Efficient and Privacy-Adaptable Mechanism -- a Federated Learning Scheme with Convergence Analysiscited by 1
  32. 2026CADC: Content Adaptive Diffusion-Based Generative Image Compressioncited by 1
  33. 2026Deep Randomized Distributed Function Computation (DeepRDFC): Neural Distributed Channel Simulationcited by 1
  34. 2021End-to-End Image Compression with Probabilistic Decodingcited by 0
  35. 2022On One-Bit Quantizationcited by 0
  36. 2022Latent Discretization for Continuous-time Sequence Compressioncited by 0
  37. 2023DietCNN: Multiplication-free Inference for Quantized CNNscited by 0
  38. 2023RAND: Robustness Aware Norm Decay For Quantized Seq2seq Modelscited by 0

50 most cited of 60 All 60 (JSON)