Research map / Probabilistic and scientific modeling / Bayesian optimization
Bayesian Optimization over Hybrid Spaces
Aryan Deshwal, Syrine Belakaria, Janardhan Rao Doppa
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 HyBO instead of the strongest listed baseline | Neural-network hyperparameter tuning · blood_transfusion | accuracy: 76.978 (0.455) -> 77.819 (0.463) | Improved |
| Use HyBO instead of the strongest listed baseline | Neural-network hyperparameter tuning · kc1 | accuracy: 85.637 (0.069) -> 85.466 (0.116) | Hurt |
| Use HyBO instead of the strongest listed baseline | Neural-network hyperparameter tuning · vehicle | accuracy: 83.669 (1.013) -> 86.104 (0.894) | Improved |
| Use HyBO instead of the strongest listed baseline | Neural-network hyperparameter tuning · segment | accuracy: 89.986 (0.692) -> 91.433 (0.277) | Improved |
| Use HyBO instead of the strongest listed baseline | Neural-network hyperparameter tuning · cnae | accuracy: 95.691 (0.082) -> 95.644 (0.135) | Hurt |
| Use HyBO instead of the strongest listed baseline | Neural-network hyperparameter tuning · jasmine | accuracy: 77.460 (0.189) -> 77.121 (0.172) | Hurt |
| Use HyBO instead of G-M et al. | Hybrid BO · Synthetic Function 1 | best function value: 99.4 -> 79.7 | Improved |
| Use HyBO instead of G-M et al. | Hybrid BO · Synthetic Function 2 | best function value: 420 -> 394.6 | Improved |
| Use HyBO instead of G-M et al. | Hybrid BO · Synthetic Function 3 | best function value: 143 -> 81.1 | Improved |
| Use HyBO instead of G-M et al. | Hybrid BO · Synthetic Function 4 | best function value: 458 -> 395.2 | Improved |
| Remove hyperparameter marginalization (ablation) | HyBO · Synthetic benchmarks | best function value | Mixed |
| Add hyperparameter marginalization (ablation) | HyBO without marginalization · Synthetic and real-world benchmarks | convergence speed | Improved |
Closest papers by meaning
- Omnipresent Yet Overlooked: Heat Kernels in Combinatorial Bayesian Optimization (NeurIPS 2025 · similarity 0.86)
- Joint Composite Latent Space Bayesian Optimization (ICML 2024 · similarity 0.84)
- BARK: A Fully Bayesian Tree Kernel for Black-box Optimization (ICML 2025 · similarity 0.84)
- Boundary Exploration for Bayesian Optimization With Unknown Physical Constraints (ICML 2024 · similarity 0.83)
- Learning Surrogates for Offline Black-Box Optimization via Gradient Matching (ICML 2024 · similarity 0.83)
- Posterior Inference with Diffusion Models for High-dimensional Black-box Optimization (ICML 2025 · similarity 0.83)
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.
