Kernel Ridgeless Regression is Inconsistent in Low Dimensions

Add code
Jun 02, 2022
Daniel Beaglehole, Mikhail Belkin, Parthe Pandit
Figure 1 for Kernel Ridgeless Regression is Inconsistent in Low Dimensions
Figure 2 for Kernel Ridgeless Regression is Inconsistent in Low Dimensions

Share this with someone who'll enjoy it:

Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon

We show that kernel interpolation for a large class of shift-invariant kernels is inconsistent in fixed dimension, even with bandwidth adaptive to the training set.

View paper onarxiv icon

Share this with someone who'll enjoy it:

Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon