I am new to the computer science and ML community. I learn best by doing which is why I have created a project for myself to help me get to know gaussian processes and ML in general. I was pointed to this paper (http://proceedings.mlr.press/v89/uhrenholt19a.html) as a possible solution to my problem. However, I am getting caught up in the theory of it and seem to be struggling, hopefully someone can shed some light on the areas I am unsure of.
My Question is this:
In this paper it uses a gaussian process as a surrogate model and an expected improvement and lower confidence bound acquisition functions. That's fine I understand that and how it works. However, in section 3.1, it goes into the L^2 norm and chi squared distribution. I know what they are in general terms but I am having trouble applying it to this paper and making sense of it. Could someone provide a high level, maybe visual explanation like a flow chart diagram of how the L^2 norm and chi squared distribution is used in this papers acquisition functions.
Thanks everyone