Gradient Kernel Regression — mentioned by mvcalder

Tue, 12 Oct 2021 14:59:30 GMT

When I first read about the NTK I was motivated to try an experiment to see if the kernel depended on where in the parameter space one evaluated it. I was surprised to see in my simple example the answer was "no". Here is a write up I did: https://arxiv.org/pdf/2104.05874.pdf

Paper and discussion history. A mention is not an endorsement.

Gradient Kernel Regression · HackerPapers discussions

Gradient Kernel Regression — mentioned by mvcalder