Research map / Probabilistic and scientific modeling / Bayesian optimization
Parallel Bayesian Optimization of Multiple Noisy Objectives with Expected Hypervolume Improvement
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 |
|---|---|---|---|
| Integrate over uncertainty in the Pareto frontier of observed points (NEHVI) instead of using the observed Pareto frontier (EHVI) (ablation) | Noisy multi-objective BO · BraninCurrin, DTLZ2, ABR, VehicleSafety (noisy) | log hypervolume difference | Helped |
| Use NEHVI instead of plugging in the posterior mean (EHVI-PM) (ablation) | qEHVI · noisy benchmarks | log hypervolume difference | Helped |
| Use cached box decompositions instead of inclusion-exclusion principle (ablation) | qNEHVI/qEHVI · DTLZ2 batch sizes | acquisition optimization wall time | Helped |
| Use full qNEHVI instead of single-sample-path approximation qNEHVI-1 as dimensionality grows (ablation) | qNEHVI · higher-dimensional search spaces | hypervolume | Mixed |
| Increase observation noise level up to 30% of objective range | qNEHVI · noise study | relative performance vs baselines | No clear effect |
Closest papers by meaning
- Expected Hypervolume Improvement Is a Particular Hypervolume Improvement (AAAI 2025 · similarity 0.93)
- MOBO-OSD: Batch Multi-Objective Bayesian Optimization via Orthogonal Search Directions (NeurIPS 2025 · similarity 0.90)
- BOtied: Multi-objective Bayesian optimization with tied multivariate ranks (ICML 2024 · similarity 0.90)
- Simple Extensions of Single-Objective Acquisition Functions and Hedge Strategies for Multi-Objective Bayesian Optimization (NeurIPS 2026 · similarity 0.90)
- Trading Off Quality and Uncertainty Through Multi-Objective Optimisation in Batch Bayesian Optimisation (AAAI 2025 · similarity 0.89)
- Probability Distribution of Hypervolume Improvement in Bi-objective Bayesian Optimization (ICML 2024 · similarity 0.89)
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.