Research map / Learning theory and algorithms / Sample complexity
Universally Quantized Neural Compression
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 test-time quantization (UN + Q) instead of universal quantization (UN + UQ) for a model trained with uniform noise (ablation) | linear model and hyperprior model · Kodak | rate-distortion (bpp vs PSNR) | Helped |
| add annealed soft rounding to the uniform noise channel with universal quantization (UN + UQ + SR) versus test-time quantization baseline (ablation) | linear model · Kodak | rate-distortion (bpp vs PSNR) | Helped |
| add annealed soft rounding to the uniform noise channel (UN + UQ + SR) versus test-time quantization baseline (ablation) | hyperprior model · Kodak | rate-distortion (bpp vs PSNR) | Helped |
| use expected (analytically integrated) gradients for soft rounding with s_7 and r_16 (ablation) | linear model UN + UQ + SR · Kodak | test loss / convergence speed | Helped |
| use expected gradients when alpha > 7 (annealed 1 to 16 or fixed 13) (ablation) | hyperprior UN + UQ + SR · Kodak | rate-distortion performance and training stability | Helped |
Closest papers by meaning
- Soft then Hard: Rethinking the Quantization in Neural Image Compression (ICML 2021 · similarity 0.92)
- Approaching Rate-Distortion Limits in Neural Compression with Lattice Transform Coding (ICLR 2025 · similarity 0.88)
- Progressive Compression with Universally Quantized Diffusion Models (ICLR 2025 · similarity 0.87)
- Bridging the Gap between Gaussian Diffusion Models and Universal Quantization for Image Compression (CVPR 2025 · similarity 0.87)
- On Quantizing Neural Representation for Variable-Rate Video Coding (ICLR 2025 · similarity 0.86)
- Effective Interplay between Sparsity and Quantization: From Theory to Practice (ICLR 2025 · 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.