skills.rest
OlixIgnacious
OlixIgnaciousCOMMUNITY
Explore all skills by this author →
GitHub

kaggle-optuna

Optimizes hyperparameters of Kaggle machine learning models using Optuna's TPE sampler for LightGBM, XGBoost, CatBoost, and ensembles.

1|Updated Jun 6, 2026
Search Tags:#hyperparameter optimization#kaggle#optuna#xgboost#lightgbm
One-click install
npx skills add https://github.com/OlixIgnacious/agent-skills --skill kaggle-optuna
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: kaggle-optuna
Source: https://github.com/OlixIgnacious/agent-skills/tree/main/.claude/skills/kaggle-optuna
Command: npx skills add https://github.com/OlixIgnacious/agent-skills --skill kaggle-optuna

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires optuna, lightgbm, xgboost, catboost, and includes scripts (resource) components.

What problem does it solve?

This Skill provides hyperparameter optimization for machine learning models on Kaggle, using Optuna's Tree-structured Parzen Estimator (TPE) sampler, enhancing model performance and reducing overfitting.

Core Features & Use Cases

  • Hyperparameter Optimization: Automatically tune hyperparameters for LightGBM, XGBoost, CatBoost, and neural networks.
  • Ensemble Weight Optimization: Offers an alternative to scipy hill climbing for large model pools, improving ensemble predictions.
  • Use Case: Utilize this Skill after establishing baselines in your Kaggle competition to optimize your model's hyperparameters, leading to better model performance.

Quick Start

Run the kaggle-optuna skill to optimize hyperparameters for your LightGBM model on the Kaggle competition dataset.

Frequently Asked Questions about kaggle-optuna

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I tune hyperparameters for LightGBM and XGBoost in Kaggle competitions?▼

Optimize ensemble weights by using Optuna as an alternative to scipy hill climbing for large model pools. This method efficiently searches for the best combination of predictions, improving overall ensemble accuracy.

Can I use Optuna to optimize ensemble weights for a large pool of Kaggle models?▼

Optimize ensemble weights by using Optuna as an alternative to scipy hill climbing for large model pools. This method efficiently searches for the best combination of predictions, improving overall ensemble accuracy for Kaggle submissions.

How does the TPE sampler work for GBDT model optimization?▼

The TPE sampler works for GBDT model optimization by using a probabilistic model to propose hyperparameter configurations based on past trials. It balances exploration and exploitation to efficiently find optimal parameters for models like LightGBM and CatBoost.

What libraries do I need to run Optuna hyperparameter tuning on Kaggle?▼

You need the Optuna, LightGBM, XGBoost, and CatBoost libraries installed to run hyperparameter tuning. These dependencies provide the foundational frameworks required for executing the TPE sampler and training GBDT-based models.

When should I use Optuna TPE sampling instead of scipy hill climbing for Kaggle ensembles?▼

Use Optuna TPE sampling instead of scipy hill climbing when optimizing ensemble weights for large model pools. Optuna provides a more efficient search mechanism that scales better with an increasing number of base models.

Related Skills

Explore More Data & Analytics Skills→
OlixIgnaciousOlixIgnacious
1

kaggle-baselines

Build linear, GBDT, and neural network baselines for Kaggle competitions.

Community
Advanced
OlixIgnaciousOlixIgnacious
1

kaggle-extra-training

Run seed ensembling and full-data retraining on Kaggle models.

Community
Advanced
andikarachmanandikarachman
14

split-strategy

Select train/validation/test split strategies based on data characteristics.

Community
Intermediate
snoodleboot-iosnoodleboot-io
2

hyperparameter-optimization

Explain hyperparameter tuning techniques including grid search, random search, Bayesian optimization, and reinforcement learning.

Official
Intermediate