Research map / Learning theory and algorithms / Optimal transport
An Optimal Diffusion Approach to Quadratic Rate-Distortion Problems: New Solution and Approximation Methods
Dror Freirich, Nir Weinberger
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 R2D2 diffusion-based estimator instead of NERD and WGD | R(D) estimation, 1-D Gaussian source · 1-D Gaussian N(0,1), eps in [0.05,0.95] | absolute RD estimation error | Improved |
| use R2D2 instead of NERD and WGD, which cap the rate at roughly 13 nats | R(D) estimation on speech data · Free Spoken Digit (33-dim) | reachable rate (nats): approximating rates > 20 nats vs about 13 nats | Improved |
| use R2D2 instead of NERD and WGD | R(D) estimation on image patches · CIFAR10 4x4 grayscale patches | R(D) curve | Improved |
| compare R2D2 estimate with Shannon lower bound on Gaussian mixture | R2D2 · 3-component Gaussian mixture, eps in [4e-4,1.64e-2] | R(D) vs SLB | No clear effect |
Closest papers by meaning
- Optimal Neural Compressors for the Rate-Distortion-Perception Tradeoff (NeurIPS 2025 · similarity 0.83)
- Minimum Entropy Coupling with Bottleneck (NeurIPS 2024 · similarity 0.83)
- Masked Diffusion Models as Energy Minimization (NeurIPS 2025 · similarity 0.83)
- Progressive Compression with Universally Quantized Diffusion Models (ICLR 2025 · similarity 0.82)
- Improved sampling via learned diffusions (ICLR 2024 · similarity 0.82)
- Understanding Diffusion Models by Feynman's Path Integral (ICML 2024 · similarity 0.82)
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.
