Research map / Probabilistic and scientific modeling / Variational and generative sampling
Practical lossless compression with latent variables using bits back coding
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use BB-ANS with a VAE instead of generic compression with bz2 | MNIST lossless compression · Binarized MNIST test set | bits per dimension: 0.25 -> 0.19 | Helped |
| Use BB-ANS with a VAE instead of generic compression with bz2 | MNIST lossless compression · Full MNIST test set | bits per dimension: 1.42 -> 1.41 | Helped |
| Use BB-ANS coding with a VAE rather than coding at the negative test ELBO rate | BB-ANS with VAE · Binarized MNIST test set | bits per dimension: 0.19 -> 0.19 | No clear effect |
| Use BB-ANS coding with a VAE rather than coding at the negative test ELBO rate | BB-ANS with VAE · Full MNIST test set | bits per dimension: 1.39 -> 1.41 | Hurt |
Closest papers by meaning
- Bit-Swap: Recursive Bits-Back Coding for Lossless Compression with Hierarchical Latent Variables (ICML 2019 · similarity 0.92)
- Improving Lossless Compression Rates via Monte Carlo Bits-Back Coding (ICML 2021 · similarity 0.91)
- Improving Inference for Neural Image Compression (NeurIPS 2020 · similarity 0.91)
- Robustly overfitting latents for flexible neural image compression (NeurIPS 2024 · similarity 0.87)
- Generative Latent Coding for Ultra-Low Bitrate Image Compression (CVPR 2024 · similarity 0.87)
- Learned Lossless Image Compression based on Bit Plane Slicing (CVPR 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.