Sum of squares¶
RSS(w)≜
\hat{y}_i is the predicted value of i
It can be viewed as the l_2 of error:
RSS(w) = ||\epsilon||_2^2 = \sum_{i=1}^N \epsilon_i^2
\epsilon_i =y_i - \hat{y}_i
\hat{y}_i is the predicted value of i
It can be viewed as the l_2 of error:
RSS(w) = ||\epsilon||_2^2 = \sum_{i=1}^N \epsilon_i^2
\epsilon_i =y_i - \hat{y}_i