Hyperparameter Optimization
Matt shares effective strategies for hyperparameter tuning, emphasizing the benefits of stepwise tuning to save time while improving model performance. The conversation explores the advantages of using Bayesian methods over traditional grid search, highlighting how they adaptively hone in on optimal values. Jon draws an engaging analogy between learning rates and golf clubs, illustrating the trade-offs between speed and precision in model training.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