Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
Fast Information-theoretic Bayesian Optimisation
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 |
|---|---|---|---|
| Represent the objective as a parabola and sample its minimum as hyperparameter eta instead of sampling the global minimiser | FITBO · Acquisition-function evaluation | runtime | Helped |
| Use output-space entropy about the minimum value rather than input-space entropy about the minimiser | FITBO · High-dimensional optimisation | runtime | Helped |
| Use moment matching instead of numerical integration for mixture entropy (ablation) | FITBO · Benchmark functions | optimisation performance | No clear effect |
| Use moment matching instead of numerical integration for mixture entropy (ablation) | FITBO · Real-world optimisation problems | validation loss | No clear effect |
| Use moment matching instead of numerical integration for mixture entropy (ablation) | FITBO · Acquisition-function evaluation | runtime | Helped |
| Use FITBO rather than EI | Bayesian optimisation · Branin-2D | immediate regret | Mixed |
| Use FITBO rather than EI | Bayesian optimisation · Eggholder-2D | immediate regret | Hurt |
| Use FITBO rather than competing methods | Bayesian optimisation · Eggholder-2D | distance to global minimiser | Helped |
| Use FITBO or FITBO-MM rather than competing methods | Bayesian optimisation · Hartmann-6D | immediate regret | Helped |
| Use FITBO or FITBO-MM rather than competing methods | Bayesian optimisation · Hartmann-6D | distance to global minimiser | Helped |
| Use FITBO or FITBO-MM rather than EI | Bayesian optimisation · Boston and MNIST-SVM | validation loss | Helped |
| Use FITBO or FITBO-MM rather than MES and EI | Bayesian optimisation · Cancer | validation loss | Helped |
Closest papers by meaning
- BO-Arena: An Evolving Benchmark for High-Dimensional Bayesian Optimisation (NeurIPS 2026 · similarity 0.90)
- A General Framework for User-Guided Bayesian Optimization (ICLR 2024 · similarity 0.90)
- Bayesian Optimisation with Unknown Hyperparameters: Regret Bounds Logarithmically Closer to Optimal (NeurIPS 2024 · similarity 0.88)
- Sample-efficient Bayesian Optimisation Using Known Invariances (NeurIPS 2024 · similarity 0.88)
- Bayesian Optimization with Fisher Information Geometry: Gradient Bounds and Trust-Region Methods (NeurIPS 2026 · similarity 0.88)
- Understanding High-Dimensional Bayesian Optimization (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.