how to tune parameters of custom kernel function with pipeline in scikit-learn

Question

currently I have successfully defined a custom kernel function(pre-computing the kernel matrix) using def function, and now I am using the GridSearchCV function to get the b

Answer 1

Attacking the problem from a slightly different angle - how about using an automated parameter tuning with auto-sklearn? It is a drop-in replacement of sklearn and frequently it does a better job than manually tuned parameters.