EasyDeepLearn
← All categories
Supervised Learning
Interview · flashcards

Supervised Learning

Classification, regression, evaluation and the classic bias-variance interview questions.

← LessonStart quiz →
easyfundamentalsevaluation

What is the bias-variance tradeoff?

Click, press Space or use the button below to reveal the answer
Interview-style answer
  • Bias is error from wrong assumptions (underfitting).
  • Variance is error from sensitivity to training data (overfitting).
  • Total generalization error decomposes as E[(y−f^(x))2]=Bias[f^(x)]2+Var[f^(x)]+σ2\mathbb{E}\big[(y - \hat{f}(x))^{2}\big] = \mathrm{Bias}\big[\hat{f}(x)\big]^{2} + \mathrm{Var}\big[\hat{f}(x)\big] + \sigma^{2} where σ2\sigma^{2} is the irreducible noise.
  • You reduce bias with more complex models or better features, and reduce variance with more data, regularization, or ensembling.
  • The tradeoff means you can rarely minimize both at once.
Click again to flip back
1 / 215

Shortcuts: Space/Enter flip · ← / → navigate · K = known · R = review