Search Results for author:
Found 1 papers, 0 papers with code
Characterizing Overfitting in Kernel Ridgeless Regression Through the Eigenspectrum
Our contribution is two-fold: (i) we rigorously prove the phenomena of tempered overfitting and catastrophic overfitting under the sub-Gaussian design assumption, closing an existing gap in the literature; (ii) we identify that the independence of the features plays an important role in guaranteeing tempered overfitting, raising concerns about approximating KRR generalization using the Gaussian design assumption in previous literature.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
