Principal Component Regression Dominates all Monotone Spectral Filters for Linear Regression
We compare the instance-wise, finite-sample risks of monotone spectral filters for linear regression, a broad class of estimators including principal component regression (PCR), gradient descent (GD), and ridge regression. We show that PCR dominates all monotone spectral filters: compared to any such filter, the risk o...
Juno Kim, Heng-Yu Fu, Peter L. Bartlett et al.
· 1 citation