Statistical learning refers to a set of approaches for estimating $f$ in

$$ Y = f(X) + ϵ, $$

where

2.1.1 Why Estimate $f$?

There are two main reasons for estimating $f$.

Prediction

Given a set of input $X$, we want to predict the unkown output $Y$.

We can predict $Y$ by using

$$ \hat Y = \hat f(X), $$

where