Research map / Learning theory and algorithms / Sample complexity
Sequential and Parallel Constrained Max-value Entropy Search via Information Lower Bound
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 CMES-IBO instead of CMES | Constrained Bayesian optimization · GP-derived synthetic functions | utility gap | Helped |
| Use CMES-IBO instead of competing acquisition methods | Constrained Bayesian optimization · Gardner1, G1, G7, and G10 | utility gap | Mixed |
| Use CMES-IBO instead of competing acquisition methods | Constrained Bayesian optimization · Reactor network design | utility gap | Helped |
| Use CMES-IBO instead of other methods | Constrained Bayesian optimization · CIFAR10 CNN hyperparameter optimization | utility gap | Helped |
| Use parallel CMES-IBO instead of other parallelized methods | Parallel constrained Bayesian optimization · G1, G7, and G10 | utility gap | Helped |
| Represent multiple constraints separately rather than transforming them into one minimum-margin constraint (ablation) | Constrained Bayesian optimization methods · GP-derived synthetic functions with 10 constraints | utility gap | Helped |
| Increase the number of constraints in CMES | CMES · Constrained acquisition function | acquisition value non-negativity: C > 5 | Hurt |
| Use the non-negativity-guaranteed CMES-IBO lower-bound acquisition instead of the direct CMES approximation | Constrained Bayesian optimization · Toy example with 6 and 7 constraints | acquisition value non-negativity: C = 6 and 7 | Helped |
| Use CMES-IBO rather than CMES | Constrained Bayesian optimization · G7 | utility gap | Helped |
| Use CMES-IBO rather than CMES | Constrained Bayesian optimization · G10 | utility gap: 30 | Helped |
| Estimate the MI lower bound with K Monte Carlo samples | CMES-IBO · Estimator variability | variance: ≤ 2 | Helped |
Closest papers by meaning
- Max-value Entropy Search for Efficient Bayesian Optimization (ICML 2017 · similarity 0.92)
- A Unified Framework for Entropy Search and Expected Improvement in Bayesian Optimization (ICML 2025 · similarity 0.89)
- Pareto-frontier Entropy Search with Variational Lower Bound Maximization (ICML 2025 · similarity 0.87)
- A General Framework for User-Guided Bayesian Optimization (ICLR 2024 · similarity 0.86)
- Bayesian Optimization with Fisher Information Geometry: Gradient Bounds and Trust-Region Methods (NeurIPS 2026 · similarity 0.85)
- Maximin Robust Bayesian Experimental Design (NeurIPS 2026 · 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.