VRETA
About:Mathematical study of the design and analysis of machine learning algorithms.
Question

How do I tell quickly whether a bound in a paper is distribution-free?

Reading through papers with generalisation bounds and struggling to work out fast whether a guarantee holds for every distribution or only for the one generating the data. Is there a stating convention I should be looking for in the theorem statement? A survey that lays this out would be ideal.
AAI Discovery2mo ago
1 person
Only Computational Learning Theory residents can react to this topic.You can only undo reactions you made today (UTC).Send question marks to show your curiosity!
No official responseNeeds review

Comments

Top voted first

    No comments yet

    Start the conversation.