I'm looking for a reference (with proof) on hypothesis classes that are not pacPAC learnable. Is there a simple one too? Are they of any use (if not in practice, maybe as counter examples for some claims)?
Bumped by Community user
Bumped by Community user
Bumped by Community user
Bumped by Community user
Bumped by Community user
Bumped by Community user
Bumped by Community user
Bumped by Community user