Research map / Optimization / Optimizers
Estimating the Rate-Distortion Function by Wasserstein Gradient Descent
Yibo Yang, Stephan Eckstein, Marcel Nutz, Stephan Mandt
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 L_BA rather than L_EOT for WGD (ablation) | WGD · R-D estimation | computational speed: 10 to 100 times faster | Improved |
| Alternate WGD updates with BA weight updates (ablation) | WGD · deconvolution | convergence speed | Improved |
| Use WGD instead of neural upper-bound methods | R-D estimation · MNIST | convergence speed: at least an order of magnitude faster | Improved |
| Use WGD instead of NERD at the same computation budget | R-D estimation · physics, speech, and MNIST | R-D upper-bound tightness | Improved |
| Increase the number of particles (ablation) | WGD · R-D estimation | R-D upper-bound tightness | Improved |
| Move reproduction particles rather than keeping their initial locations fixed (ablation) | particle-based R-D estimation · deconvolution | optimality gap | Improved |
| Use a particle-based method rather than the neural methods | deconvolution · uniform measure on the unit circle | reproduction-support accuracy | Improved |
| Use WGD or its hybrid variant rather than BA or NERD | R-D estimation · deconvolution across dimensions and lambda values | optimality gap | Improved |
Closest papers by meaning
- Balanced Rate-Distortion Optimization in Learned Image Compression (CVPR 2025 · similarity 0.85)
- Good, Cheap, and Fast: Overfitted Image Compression with Wasserstein Distortion (CVPR 2025 · similarity 0.85)
- Compression of Structured Data with Autoencoders: Provable Benefit of Nonlinearities and Depth (ICML 2024 · similarity 0.85)
- Approaching Rate-Distortion Limits in Neural Compression with Lattice Transform Coding (ICLR 2025 · similarity 0.85)
- Optimal Neural Compressors for the Rate-Distortion-Perception Tradeoff (NeurIPS 2025 · similarity 0.85)
- Debiased Distribution Compression (ICML 2024 · similarity 0.85)
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.
