Research map / Probabilistic and scientific modeling / Bayesian optimization
Efficient Hyperparameter Optimization for Deep Learning Algorithms Using Deterministic RBF Surrogates
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 HORD instead of GP-EI | 6-MLP hyperparameter optimization · 6-MLP (MNIST) | test set error: 1.94 (.11) -> 1.87 (.06) | Helped |
| use HORD instead of GP-EI | 8-CNN hyperparameter optimization · 8-CNN (MNIST) | test set error: 0.77(.07) -> 0.84(.04) | Hurt |
| add an initial starting point (ISP) to HORD (ablation) | 15-CNN hyperparameter optimization · 15-CNN (MNIST) | test set error: 0.94(.07) -> 0.82(.05) | Helped |
| add an initial starting point (ISP) to HORD (ablation) | 19-CNN hyperparameter optimization · 19-CNN (CIFAR-10) | test set error: 23.23(1.9) -> 20.54(1.2) | Helped |
| use HORD-ISP instead of GP-EI | 15-CNN hyperparameter optimization · 15-CNN (MNIST) | evaluations to reach baseline mean best validation error (percentage of 200): 18%(36) | Helped |
| use HORD-ISP instead of SMAC | 19-CNN hyperparameter optimization · 19-CNN (CIFAR-10) | evaluations to reach baseline mean best validation error (percentage of 200): 27%(54) | Helped |
| use HORD-ISP instead of SMAC | 19-CNN hyperparameter optimization · 19-CNN (CIFAR-10) | evaluations until significantly better best validation error: 33%(66) | Helped |
Closest papers by meaning
- BOHB: Robust and Efficient Hyperparameter Optimization at Scale (ICML 2018 · similarity 0.88)
- A Study of Bayesian Neural Network Surrogates for Bayesian Optimization (ICLR 2024 · similarity 0.86)
- Sample complexity of data-driven tuning of model hyperparameters in neural networks with structured parameter-dependent dual function (NeurIPS 2025 · similarity 0.86)
- Efficient Hyperparameter Optimization with Adaptive Fidelity Identification (CVPR 2024 · similarity 0.85)
- Bayesian Optimisation with Unknown Hyperparameters: Regret Bounds Logarithmically Closer to Optimal (NeurIPS 2024 · similarity 0.85)
- Informed Initialization for Bayesian Optimization and Active Learning (NeurIPS 2025 · similarity 0.84)
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.