Is it okay to not provide a whitelist when using the Hill-Climbing algorithm?

35 Views Asked by At

So, I'm trying to use Hill-Climbing for a Bayesian learning network. For some reasons, I do not know all of the variables that I'm going to use and hence, I cannot provide a whitelist or a blacklist when using the algorithm. Is it okay to do that, in theory? Can it lead to erroneous conclusions about the results obtained?