Beyond Grid Search: XGBoost and Optuna as the ultimate ML Optimization Combo
summary
Uses XGBoost with Optuna to replace manual grid search, wrapping the model in an objective function, using Optuna’s suggest API and Optuna pruning to cut unpromising trials. On a real imbalanced problem with about 400,000 rows and hundreds of features, pruning turns multi‑hour grid searches into runs that finish in hours instead of days and delivers small metric gains that translate to large dollar value. Also shows automated CI jobs with GPU CI runners for reproducible, parallel optimization.
AI-written summary · about
chapters (8)
- 0:00Introduction and motivation
- 1:38Defining the core problem
- 8:24The optuna recipe
- 10:47Demo and pruning benefits
- 13:25Advanced features
- 15:40Production and CI/CD integration
- 17:44Optimizing developer workflows
- 20:33Q&A session
related talks
41mOptimizing Machine Learning Models
18mBest Practices for Hyperparameter Optimization
24mUsing Bayesian Optimization to Tune Machine Learning Models
18mAlexandra Johnson, Software Engineer, SigOpt, NYC 2017
27mAutomating XGBoost Hyperparameter Tuning with Agentic AI
03mDBTB INT Scott Clark r
38mA Guide to Modern Hyperparameters Turning Algorithms
48mOptimize the Right Thing