The only programs allowed in the Solomonoff distribution are ones that don’t have any extended versions that produce the same output observed so far.
Did not know that! It seems like that would leave some probability mass unassigned, how do you rebalance? Even if you succeed, it seems likely that (for large enough outputs) there’ll be lots of programs that have epsilon difference—that are basically the same, for all practical purposes.
Did not know that! It seems like that would leave some probability mass unassigned, how do you rebalance? Even if you succeed, it seems likely that (for large enough outputs) there’ll be lots of programs that have epsilon difference—that are basically the same, for all practical purposes.
Normalize!
Solomonoff induction is just defined for binary data. Differences are a minimum of 1 bit,, which is enough.