Run Bayesian hyperparameter optimization for LightGBM, XGBoost, and CatBoost models with Optuna.
npx skills add https://github.com/KameniAlexNea/gladius-agent --skill hpo
Please help me install this Agent Skill. Skill: hpo Source: https://github.com/KameniAlexNea/gladius-agent/tree/main/gladius/utils/templates/skills/hpo Command: npx skills add https://github.com/KameniAlexNea/gladius-agent --skill hpo
This Skill automates the process of finding the optimal hyperparameters for machine learning models, saving significant manual effort and computational resources.
Run the hyperparameter optimization script for LightGBM using your data.
High-intent search queries and answers about installing and using this skill.
Automate hyperparameter tuning for XGBoost and LightGBM by applying Optuna's Bayesian optimization with TPE sampling. This process searches for optimal parameters to improve model performance and uses fold-level pruning to save computational resources.
Bayesian hyperparameter optimization uses past trial results to intelligently sample the next parameters, making it more efficient than random search. Use it for gradient boosting models like LightGBM, XGBoost, and CatBoost to achieve peak performance after establishing a baseline.
Yes, you can resume an interrupted hyperparameter search because the optimization results are saved to an SQLite database. This persistence mechanism allows you to stop and restart the Optuna study without losing previous trial data.
Yes, you must install Optuna, LightGBM, XGBoost, and CatBoost libraries separately before execution. These dependencies are required for the Skill to run the hyperparameter search templates and train the corresponding gradient boosting models.
Fold-level pruning improves search efficiency by using Optuna's MedianPruner to terminate unpromising training trials early. This cuts off evaluations that are unlikely to beat the current best score, significantly saving compute time during optimization.
HomericIntelligenceExecute model training pipelines with forward and backward passes, gradient updates, and checkpoint management.
OlixIgnaciousOptimizes hyperparameters of Kaggle machine learning models using Optuna's TPE sampler for LightGBM, XGBoost, CatBoost, and ensembles.
nahisahoDevelop end-to-end ML models with training, evaluation, deployment, and MLOps.
snoodleboot-ioExplain hyperparameter tuning techniques including grid search, random search, Bayesian optimization, and reinforcement learning.
