Bias Variance Tradeoff
In plain terms
The balance between a model's simplicity and flexibility.
Going deeper
The bias-variance tradeoff explains that overly simple models underfit (high bias) and overly complex ones overfit (high variance); good models balance both. It's central to generalization.
Under the hood
Total error decomposes into bias, variance, and noise; regularization and data size shift the balance.
Examples
Model selection, overfitting/underfitting, regularization, generalization.
Think of it like...
Like aiming: consistent-but-off (bias) versus scattered-but-centered (variance), you want both tight and centered.