A Dilemma for Solomonoff Prediction

Philosophy of Science 90 (2):288-306 (2023)
  Copy   BIBTEX

Abstract

The framework of Solomonoff prediction assigns prior probability to hypotheses inversely proportional to their Kolmogorov complexity. There are two well-known problems. First, the Solomonoff prior is relative to a choice of Universal Turing machine. Second, the Solomonoff prior is not computable. However, there are responses to both problems. Different Solomonoff priors converge with more and more data. Further, there are computable approximations to the Solomonoff prior. I argue that there is a tension between these two responses. This is because computable approximations to Solomonoff prediction do not always converge.

Similar books and articles

Solomonoff Prediction and Occam’s Razor.Tom F. Sterkenburg - 2016 - Philosophy of Science 83 (4):459-479.
Universal Prediction: A Philosophical Investigation.Tom F. Sterkenburg - 2018 - Dissertation, University of Groningen
Should physicians be bayesian agents?M. Wayne Cooper - 1992 - Theoretical Medicine and Bioethics 13 (4).
Accommodation, Prediction and Bayesian Confirmation Theory.Colin Howson - 1988 - PSA: Proceedings of the Biennial Meeting of the Philosophy of Science Association 1988:381 - 392.
Uncommon priors require origin disputes.Robin Hanson - 2006 - Theory and Decision 61 (4):319-328.

Analytics

Added to PP
2022-06-13

Downloads
457 (#43,062)

6 months
142 (#25,579)

Historical graph of downloads
How can I increase my downloads?

Author's Profile

Sven Neth
University of Pittsburgh

Citations of this work

Better Foundations for Subjective Probability.Sven Neth - forthcoming - Australasian Journal of Philosophy.
Non-Ideal Decision Theory.Sven Neth - 2023 - Dissertation, University of California, Berkeley

Add more citations