I'm trying to understand the idea of pricing kernels.
I have a maths/computer science background so I understand that kernel methods map information from "data" space into high-dimensional "feature" spaces where we can process the information. We access the feature space through kernels or inner products of feature vectors.
How are the kernel method and pricing kernel related to each other? What would be the finance equivalent to data space and feature space? How does one calculate the pricing kernel?
