Optimize machine learning model settings efficiently.
Hyperparameter Tuning Expert
Optuna, Ray Tune, Bayesian Optimization
Best for
- ▸Optimizing XGBoost hyperparameters using Bayesian optimization with Optuna for tabular data
- ▸Tuning neural network architecture and training hyperparameters with Ray Tune and ASHA pruning
- ▸Setting up distributed hyperparameter search across GPU clusters for large model training
- ▸Implementing multi-fidelity optimization to reduce training time while finding optimal configurations
What you'll get
- ▸Complete Optuna study configuration with TPE sampler, search space definitions using log-uniform distributions, MedianPruner setup, and cross-validation integration
- ▸Ray Tune experiment with ASHA scheduler configuration, resource allocation strategy, and distributed training setup with proper checkpointing
- ▸Analysis framework with parameter importance plots, optimization history visualization, and statistical significance testing of results
Model type, dataset characteristics, evaluation metric, computational budget, and current baseline performance to design optimal tuning strategy.
Complete hyperparameter optimization setup with search space definition, optimization strategy selection, cross-validation configuration, and result analysis framework.
What's inside
“You are a Hyperparameter Tuning Expert. You optimize machine learning model configurations systematically using Bayesian optimization, multi-fidelity methods, and distributed search strategies across tree-based models, neural networks, and ensemble methods. - Diagnose complete context (model family,...”
Covers
Not designed for ↓
- ×Model architecture design or feature engineering decisions
- ×Data preprocessing or cleaning workflows
- ×Model interpretation or explainability analysis
- ×Production model deployment and monitoring
SupaScore
90▼
Evidence Policy
Standard: no explicit evidence policy.
Research Foundation: 7 sources (3 academic, 1 industry frameworks, 2 official docs, 1 books)
This skill was developed through independent research and synthesis. SupaSkills is not affiliated with or endorsed by any cited author or organisation.
Version History
v5.5 final distill
Pipeline v4: rebuilt with 3 helper skills
Initial release
Prerequisites
Use these skills first for best results.
Works well with
Need more depth?
Specialist skills that go deeper in areas this skill touches.
Common Workflows
Complete Model Development Pipeline
End-to-end workflow from feature engineering through hyperparameter optimization to model evaluation and deployment
© 2026 Kill The Dragon GmbH. This skill and its system prompt are protected by copyright. Unauthorised redistribution is prohibited. Terms of Service · Legal Notice