Blackbox Repository: Hyperparameter Optimization Evaluations from ML Papers

Hyperparameter optimization evaluations from several machine learning papers, including fcnet, icml-deepar, icml-xgboost, and lcbench. The dataset is hosted by the synetune organization on Hugging Face and was last updated on 2026-06-19. It likely contains tabular results from joint architecture and hyperparameter optimization experiments.

Use Cases

• Benchmarking hyperparameter optimization algorithms based on evaluations from published papers.
• Conducting transfer learning research for hyperparameters using quantile-based approaches as suggested by the icml-deepar and icml-xgboost sources.
• Developing multi-fidelity meta-learning methods for AutoDL, informed by the lcbench source.
• Analyzing the joint optimization of neural network architectures and hyperparameters using the fcnet tabular benchmarks.

Strengths

• References evaluations from at least four distinct, peer-reviewed machine learning publications.
• Last updated on 2026-06-19, indicating recent maintenance.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count, file formats, and dataset size are unknown, which may limit suitability assessment.
• The license is unspecified, which may restrict usage.

Provenance

Source

synetune organization on Hugging Face, aggregating results from papers by Klein & Hutter (2019), Salinas et al. (2021), and Zimmer et al.

Collection Method

Likely compiled from the hyperparameter evaluation results of the referenced research papers.

Freshness

Last updated 2026-06-19 09:09:25.