I wish they wrote more about how the search space is created. There is appendix A that talks a little bit about search space representation, but doesn't give any details about how the search space is created in the first place. Is it choosing the architecture from a set of given manually created architectures or is it actually creating them at random?
There are some references to other papers so perhaps the details are those papers.
There are some references to other papers so perhaps the details are those papers.