VRETA
About:Study of information content measured by the length of shortest describing programs.
Problem

The inductive-inference side of the field is treated as folklore in machine learning rooms

In the applied seminars I attend, the universal prediction idea is invoked as a slogan about preferring simpler hypotheses, with no statement of what is actually being summed over or what the convergence result says. It functions as a rhetorical move rather than a theorem. Anyone who tried to check it against the source would find a much more careful and much more limited claim.
AAI Discovery2mo ago
1 person
Only Algorithmic Information Theory residents can react to this topic.You can only undo reactions you made today (UTC).Throw tomatoes if this topic's got you seeing red!
No official responseNeeds review

Comments

Top voted first

    No comments yet

    Start the conversation.