Research map / Probabilistic and scientific modeling / Bayesian optimization
CO-BED: Information-Theoretic Contextual Optimization via Bayesian Experimental Design
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 transductive CMV-EIG design optimization | CO-BED · Continuous actions, 40D design | regret: 0.051 ± 0.001 -> 0.044 ± 0.001 | Helped |
| Use transductive CMV-EIG design optimization | CO-BED · Discrete treatments, 10D design | MSE(m*): 0.620 ± 0.024 -> 0.594 ± 0.025 | Helped |
| Use transductive CMV-EIG design optimization | CO-BED · Discrete treatments, 10D design | regret: 1.112 ± 0.035 -> 1.152 ± 0.035 | No clear effect |
| Set fixed Gumbel-Softmax temperature to 0.1 instead of moderate or high temperature (ablation) | CO-BED discrete-action design · Discrete-action parametric model | CMV-EIG: 4.7 and 4.9 | Hurt |
| Use moderate or high fixed Gumbel-Softmax temperature (tau=2.0 or tau=10.0) (ablation) | CO-BED discrete-action design · Discrete-action parametric model | CMV-EIG | No clear effect |
| Disable temperature annealing (ablation) | CO-BED discrete-action design · Discrete-action parametric model | CMV-EIG | No clear effect |
| Use temperature annealing (ablation) | CO-BED discrete-action design · Discrete-action parametric model | training stability | Helped |
Closest papers by meaning
- A Unified Framework for Entropy Search and Expected Improvement in Bayesian Optimization (ICML 2025 · similarity 0.86)
- Maximin Robust Bayesian Experimental Design (NeurIPS 2026 · similarity 0.86)
- Contextual Optimization Under Model Misspecification: A Tractable and Generalizable Approach (ICML 2025 · similarity 0.86)
- In-Context Black-Box Optimization with Unreliable Feedback (NeurIPS 2026 · similarity 0.85)
- On Estimating the Gradient of the Expected Information Gain in Bayesian Experimental Design (AAAI 2024 · similarity 0.85)
- Boundary Exploration for Bayesian Optimization With Unknown Physical Constraints (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.