mlsanityData to 7 Oct 2026

Parallel Neural Local Lossless Compression

arXiv 2201.05213 ↗First posted 13 Jan 2022eess.IV cs.LG stat.MLcited by 4

Not on the map. Why?

Abstract (arXiv)

The recently proposed Neural Local Lossless Compression (NeLLoC), which is based on a local autoregressive model, has achieved state-of-the-art (SOTA) out-of-distribution (OOD) generalization performance in the image compression task. In addition to the encouragement of OOD generalization, the local model also allows parallel inference in the decoding stage. In this paper, we propose two parallelization schemes for local autoregressive models. We discuss the practicalities of implementing the schemes and provide experimental evidence of significant gains in compression runtime compared to the previous, non-parallel implementation.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 19 of its 30 references that are in the map. First posted on arXiv 13 Jan 2022.

Builds on

19 of 30 references.

References · 19

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2013Auto-Encoding Variational Bayescited by 3,980
  3. 2019Generating Long Sequences with Sparse Transformerscited by 1,523
  4. 2019Generating Diverse High-Fidelity Images with VQ-VAE-2cited by 1,376
  5. 2021Variational Diffusion Modelscited by 1,145
  6. 2016Pixel Recurrent Neural Networkscited by 814
  7. 2017PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modificationscited by 415
  8. 2019Practical Lossless Compression with Latent Variables using Bits Back Codingcited by 85
  9. 2019Integer Discrete Flows and Lossless Compressioncited by 82
  10. 2017Parallel Multiscale Autoregressive Density Estimationcited by 71
  11. 2016PixelVAE: A Latent Variable Model for Natural Imagescited by 69
  12. 2020Understanding Anomaly Detection with Deep Invertible Networks through Hierarchies of Distributions and Featurescited by 64
7 more
  1. 2021Hierarchical VAEs Know What They Don't Knowcited by 58
  2. 2019Bit-Swap: Recursive Bits-Back Coding for Lossless Compression with Hierarchical Latent Variablescited by 51
  3. 2019HiLLoC: Lossless Image Compression with Hierarchical Latent Variable Modelscited by 36
  4. 2020IDF++: Analyzing and Improving Integer Discrete Flows for Lossless Compressioncited by 35
  5. 2021On the Out-of-distribution Generalization of Probabilistic Image Modellingcited by 32
  6. 2021iFlow: Numerically Invertible Flows for Efficient Lossless Compression via a Uniform Codercited by 25
  7. 2021Improving Lossless Compression Rates via Monte Carlo Bits-Back Codingcited by 19

Built on by

Cited by year

Citing papers per year: 2022: 4.

4 papers.

  1. 2022Deep Lossy Plus Residual Coding for Lossless and Near-lossless Image Compressioncited by 21
  2. 2022Generalization Gap in Amortized Inferencecited by 10
  3. 2022Improving VAE-based Representation Learningcited by 6
  4. 2022Multi-Scale Architectures Matter: On the Adversarial Robustness of Flow-based Lossless Compressioncited by 0