Research map / Probabilistic and scientific modeling / Bayesian optimization
Sequential Bayesian Experimental Design with Variable Cost Structure
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 marginal-utility refinement (mu) instead of action elimination (ae) | BOEDIR · Gaussian MRF, cost to reach target performance | computational cost | Helped |
| use marginal-utility refinement (mu) instead of LUCB | BOEDIR · Gaussian MRF, cost to reach target performance | computational cost | Helped |
| use ae instead of mu when posterior cost is low | BOEDIR · Gaussian MRF | computational cost | Hurt |
| use LUCB instead of mu when posterior inference is expensive | BOEDIR · Gaussian MRF | computational cost | Hurt |
| use mu instead of single-bound proxy bed-lb | BOED · Gaussian MRF, fixed budget | negative regret | No clear effect |
| use mu instead of upper-bound proxy bed-ub | BOED · Gaussian MRF, fixed budget | negative regret | Helped |
| move from scarce to broad to abundant motif | BOEDIR mu · Gaussian MRF | computational cost | Hurt |
| relax target performance guarantee | BOEDIR · Gaussian MRF | computational cost | Helped |
| use mu instead of ae with parallelized sampler | BOEDIR · Multi-object tracking | computational cost | Helped |
| use mu instead of ae with serial sampler | BOEDIR · Multi-object tracking | computational cost | No clear effect |
| use iterative refinement (mu/ae) instead of full-budget bed-lb | BOEDIR · Multi-object tracking | cost and mode entropy | Helped |
| use mu on the scarce motif versus ae and lucb | BOEDIR · Gaussian MRF scarce motif | computational cost | No clear effect |
Closest papers by meaning
- Maximin Robust Bayesian Experimental Design (NeurIPS 2026 · similarity 0.90)
- Bayesian Experimental Design Via Contrastive Diffusions (ICLR 2025 · similarity 0.88)
- On Estimating the Gradient of the Expected Information Gain in Bayesian Experimental Design (AAAI 2024 · similarity 0.88)
- Amortized Bayesian Experimental Design for Decision-Making (NeurIPS 2024 · similarity 0.87)
- Bayesian Adaptive Calibration and Optimal Design (NeurIPS 2024 · similarity 0.87)
- PASOA- PArticle baSed Bayesian Optimal Adaptive design (ICML 2024 · 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.