Research map / Probabilistic and scientific modeling / Variational and generative sampling
Proximal-Based Generative Modeling for Bayesian Inverse Problems
Boyang Zhang, Zhiguo Wang, Ya-Feng Liu
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 |
|---|---|---|---|
| increase sampling iterations K from 0 to 5 (ablation) | PGM · Toy quadratic program (beta=10) | Feasibility: 0.00% -> 97.43% | Improved |
| increase sampling iterations K from 5 to 20 (ablation) | PGM · Toy quadratic program (beta=10) | Feasibility: 97.43% -> 99.73% | Improved |
| increase inverse temperature beta from 0 to 10 (ablation) | PGM · Toy quadratic program (K=10) | Optimality gap: 0.2365 -> 0.0164 | Improved |
| increase inverse temperature beta from 0 to 10 (ablation) | PGM · Toy quadratic program (K=10) | Feasibility: 99.90% -> 99.61% | Hurt |
| replace DPS with PGM | FFHQ super-resolution 4x · FFHQ | PSNR: 28.47 -> 29.82 | Improved |
| replace DPS with PGM | FFHQ super-resolution 4x · FFHQ | SSIM: 0.793 -> 0.956 | Improved |
| replace ReSample with PGM | CelebA-HQ Gaussian deblurring · CelebA-HQ | PSNR: 30.69 -> 31.52 | Improved |
| replace DPS with PGM for sampling speed | FFHQ sampling · FFHQ | Sampling time: 36 s -> 4 s | Improved |
| replace DPS with PGM for memory | FFHQ · FFHQ | Total memory: 5369 MB -> 4682 MB | Improved |
| replace DAPS with PGM (NFEs and sampling time) | ImageNet-100 · ImageNet-100 | NFEs: 1000 -> 100 | Improved |
| replace DeepONet with PGM | MNIST inpainting · MNIST | PSNR: 28.1062 -> 28.6867 | Improved |
Closest papers by meaning
- Beyond Scores: Proximal Diffusion Models (NeurIPS 2025 · similarity 0.90)
- Provably Robust Score-Based Diffusion Posterior Sampling for Plug-and-Play Image Reconstruction (NeurIPS 2024 · similarity 0.88)
- Solving Inverse Problems with FLAIR (NeurIPS 2025 · similarity 0.88)
- A Variational Perspective on Solving Inverse Problems with Diffusion Models (ICLR 2024 · similarity 0.87)
- On Inference Stability for Diffusion Models (AAAI 2024 · similarity 0.87)
- A Mixture-Based Framework for Guiding Diffusion Models (ICML 2025 · similarity 0.87)
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.
