Bias-Variance Tradeoff

Summary

High-bias models underfit (too simple), high-variance models overfit (too sensitive to training data) — the central tension every model-tuning decision navigates.

• 1Plot training vs. validation error as model complexity increases to see the tradeoff visually.
• 2Diagnose an underfitting vs. an overfitting model from learning curves.
• 3Learn which techniques reduce bias (more features, complex models) vs. variance (regularization, more data).