Hyperparameter Tuning Insights
Matt discusses the importance of balancing hyperparameters to improve model performance, particularly with XGBoost, which often overfits out of the box. He highlights the advantages of using the Hyperopt library for efficient hyperparameter tuning, allowing for a more nuanced exploration of parameter distributions rather than relying solely on grid search methods. This approach not only saves time but also enhances the chances of finding optimal model settings.In this clip
From this podcast
Super Data Science: ML & AI Podcast with Jon Krohn
681: XGBoost: The Ultimate Classifier — with Matt Harrison
Related Questions