Suppose we are doing ordinary least-squares linear regression with a fictitious dimension. Which of the following changes can never make the cost function’s value on the training data smaller?  A: Discard the fictitious dimension (i.e., don’t append a 1 to every sample point).  B: Append quadratic features to each sample point.  C: Project the sample points onto a lower-dimensional subspace with PCA (without changing the labels) and perform regression on the projected points.  D: Center the design matrix (so each feature has mean zero).

icon
Related questions
Question

Suppose we are doing ordinary least-squares linear regression with a fictitious dimension. Which of the
following changes can never make the cost function’s value on the training data smaller?
 A: Discard the fictitious dimension (i.e., don’t append a 1 to every sample point).

 B: Append quadratic features to each sample point.
 C: Project the sample points onto a lower-dimensional subspace with PCA (without changing the labels) and
perform regression on the projected points.
 D: Center the design matrix (so each feature has mean zero).

Expert Solution
steps

Step by step

Solved in 6 steps with 3 images

Blurred answer