Research map / Image generation / Fast diffusion sampling
Scaling Bayesian Experimental Design to High-Dimensions with Information-Guided Diffusion
Adhi Saravanan, Rik Knowles, Gavin Kerrigan, Tom Rainforth
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 |
|---|---|---|---|
| guide the diffusion model with EIG (DiffBED) instead of directly optimising EIG (standard BED) | DiffBED · Source location finding | L2 error | Improved |
| enlarge the candidate pool for Rank selection (5 to 1000 candidates) (ablation) | Rank baseline · Source location finding | L2 error: 1000 vs. 5 | Hurt |
| use DiffBED instead of standard BED on image search | DiffBED · CelebA and MNIST search | cosine similarity | Improved |
| guide with EIG instead of marginal predictive entropy (ablation) | DiffBED · image search | cosine similarity | Improved |
| generate one guided design set instead of ranking 1000 pool candidates | DiffBED vs Rank (Pool) · CelebA search | cosine similarity: 1 design set vs 1 000 candidate design sets | Improved |
| use DiffBED instead of Rank (Pool) with Stable Diffusion prior | DiffBED · Zappos search (512x512) | cosine similarity | No clear effect |
Closest papers by meaning
- Bayesian Experimental Design Via Contrastive Diffusions (ICLR 2025 · similarity 0.89)
- BayesDiff: Estimating Pixel-wise Uncertainty in Diffusion via Bayesian Inference (ICLR 2024 · similarity 0.87)
- Posterior Inference with Diffusion Models for High-dimensional Black-box Optimization (ICML 2025 · similarity 0.86)
- BUFF: Bayesian Uncertainty Guided Diffusion Probabilistic Model for Single Image Super-Resolution (AAAI 2025 · similarity 0.85)
- Devil is in the Details: Density Guidance for Detail-Aware Generation with Flow Models (ICML 2025 · similarity 0.85)
- Diffusion Models Without Attention (CVPR 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.
