mlsanityData to 14 Oct 2026

Algorithms for the Communication of Samples

arXiv 2110.12805 ↗First posted 25 Oct 2021cs.IT math.IT stat.MLcited by 34

Not on the map. Why?

Abstract (arXiv)

The efficient communication of noisy data has applications in several areas of machine learning, such as neural compression or differential privacy, and is also known as reverse channel coding or the channel simulation problem. Here we propose two new coding schemes with practical advantages over existing approaches. First, we introduce ordered random coding (ORC) which uses a simple trick to reduce the coding cost of previous approaches. This scheme further illuminates a connection between schemes based on importance sampling and the so-called Poisson functional representation. Second, we describe a hybrid coding scheme which uses dithered quantization to more efficiently communicate samples from distributions with bounded support.

Key facts. Cited by 34 papers in the map (data through 14 Oct 2026). Builds on 10 of its 40 references that are in the map. First posted on arXiv 25 Oct 2021.

Builds on

10 of 40 references.

References · 10

  1. 2013Auto-Encoding Variational Bayescited by 4,053
  2. 2016End-to-end Optimized Image Compressioncited by 696
  3. 2014A* Samplingcited by 151
  4. 2019Variable Rate Deep Image Compression With a Conditional Autoencodercited by 114
  5. 2019Practical Lossless Compression with Latent Variables using Bits Back Codingcited by 86
  6. 2020Breaking the Communication-Privacy-Accuracy Trilemmacited by 68
  7. 2020Universally Quantized Neural Compressioncited by 64
  8. 2018Minimal Random Code Learning: Getting Bits Back from Compressed Model Parameterscited by 58
  9. 2020Compressing Images by Encoding Their Latent Representations with Relative Entropy Codingcited by 39
  10. 2021On the advantages of stochastic encoderscited by 28

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 1; 2022: 7; 2023: 6; 2024: 6; 2025: 6; 2026: 8.

34 papers.

Sort:

By area:

  1. 2022Lossy Image Compression with Conditional Diffusion Modelscited by 170
  2. 2022Lossy Compression with Gaussian Diffusioncited by 90
  3. 2022Multi-Realism Image Compression with a Conditional Generatorcited by 80
  4. 2022An Introduction to Neural Data Compressioncited by 79
  5. 2023High-Fidelity Image Compression with Score-based Generative Modelscited by 54
  6. 2022Lossy Image Compression with Quantized Hierarchical VAEscited by 35
  7. 2023QARV: Quantization-Aware ResNet VAE for Lossy Image Compressioncited by 32
  8. 2025Compressed Image Generation with Denoising Diffusion Codebook Modelscited by 28
  9. 2023Compression with Bayesian Implicit Neural Representationscited by 25
  10. 2025Lossy Compression with Pretrained Diffusion Modelscited by 25
  11. 2023Computationally-Efficient Neural Image Compression with Shallow Decoderscited by 23
  12. 2021Towards Empirical Sandwich Bounds on the Rate-Distortion Functioncited by 14
22 more
  1. 2024Progressive Compression with Universally Quantized Diffusion Modelscited by 10
  2. 2022Neural Estimation of the Rate-Distortion Function With Applications to Operational Source Codingcited by 9
  3. 2024Universal Exact Compression of Differentially Private Mechanismscited by 8
  4. 2023Adaptive Compression in Federated Learning via Side Informationcited by 6
  5. 2026Dual-Representation Image Compression at Ultra-Low Bitrates via Explicit Semantics and Implicit Texturescited by 5
  6. 2024Rejection-Sampled Universal Quantization for Smaller Quantization Errorscited by 4
  7. 2024Some Notes on the Sample Complexity of Approximate Channel Simulationcited by 4
  8. 2024Accelerating Relative Entropy Coding with Space Partitioningcited by 4
  9. 2025List-Level Distribution Coupling with Applications to Speculative Decoding and Lossy Compressioncited by 4
  10. 2023Semantic Communication of Learnable Conceptscited by 2
  11. 2025Optimal Neural Compressors for the Rate-Distortion-Perception Tradeoffcited by 2
  12. 2026Compression as Adaptation: Implicit Visual Representation with Diffusion Foundation Modelscited by 2
  13. 2022Latent Discretization for Continuous-time Sequence Compressioncited by 1
  14. 2025Speculative Sampling via Exponential Racescited by 1
  15. 2025Training-Free Vector Quantization via Gaussian VAEscited by 1
  16. 2026Requential Coding: Pushing the Limits of Model Compression with Self-Generated Training Datacited by 1
  17. 2024Minimal Communication-Cost Statistical Learningcited by 0
  18. 2026Remote Action Generation: Remote Control with Minimal Communicationcited by 0
  19. 2026Few-step Generative Models as Lossy Compressioncited by 0
  20. 2026Scalable Discrete-to-Continuous Channel Simulation for Compression and Privacycited by 0
  21. 2026Watermarkable Multi-Draft Speculative Sampling via Poisson Processescited by 0
  22. 2026Universal Bounds for Self-Normalized Kullback-Leibler Estimationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Generative Decompression: Optimal Lossy Decoding Against Distribution Mismatch
  2. 2021Efficient Randomized Subspace Embeddings for Distributed Optimization under a Communication Budget
  3. 2025Masked Diffusion Models are Secretly Learned-Order Autoregressive Models
  4. 2024Latency-Distortion Tradeoffs in Communicating Classification Results over Noisy Channels
  5. 2021Theoretically Better and Numerically Faster Distributed Optimization with Smoothness-Aware Quantization Techniques
  6. 2025Dataset Distillation as Data Compression: A Rate-Utility Perspective
  7. 2021Learned transform compression with optimized entropy encoding
  8. 2023Neural Distributed Compressor Discovers Binning ↗