I would have just answered “It depends on what you want to do”, with there being no set best prior/Universal Turing Machine, because of theorems like the No Free Lunch theorem (and more generally a takeaway from learning/computational theories is that there is no one best prior that was always justified, contrary to the ancient philosopher’s hopes).
I will propose an answer to No Free Lunch in an upcoming paper about Solomonoff induction. It is indeed subtle and important. In the interim, Schurz’ book “Hume’s Problem Solved” is a pretty good take. Schurz and Wolpert seem to argue against each other in their writing about NFL; I’ll explain later why I think they’re both right.
I would have just answered “It depends on what you want to do”, with there being no set best prior/Universal Turing Machine, because of theorems like the No Free Lunch theorem (and more generally a takeaway from learning/computational theories is that there is no one best prior that was always justified, contrary to the ancient philosopher’s hopes).
Then you would have been wrong. No Free Lunch Theorems do not bind to reality.
I will propose an answer to No Free Lunch in an upcoming paper about Solomonoff induction. It is indeed subtle and important. In the interim, Schurz’ book “Hume’s Problem Solved” is a pretty good take. Schurz and Wolpert seem to argue against each other in their writing about NFL; I’ll explain later why I think they’re both right.