Provable limitations of kernel methods

Simple demonstration of the limitations of kernel methods, even if the training data points can be chosen (the latter makes parity with noise easy to learn for example). Based on the work of Zeyuan Allen-Zhu and Yuanzhi Li arxiv.org/abs/2001.04413 .

[@aaryanbhagat4852]

Liked your explanation, waiting for more!
Also I think timestamping your content ( for videos greater than 30 min according to me ), will do great benefit to your audience!