Skip to main content Accessibility help
×
Home

THE NO FREE LUNCH THEOREM: BAD NEWS FOR (WHITE'S ACCOUNT OF) THE PROBLEM OF INDUCTION

  • Gerhard Schurz

Abstract

White (2015) proposes an a priori justification of the reliability of inductive prediction methods based on his thesis of induction-friendliness. It asserts that there are by far more induction-friendly event sequences than induction-unfriendly event sequences. In this paper I contrast White's thesis with the famous no free lunch (NFL) theorem. I explain two versions of this theorem, the strong NFL theorem applying to binary and the weak NFL theorem applying to real-valued predictions. I show that both versions refute the thesis of induction-friendliness. In the conclusion I argue that an a priori justification of the reliability of induction based on a uniform probability distribution over possible event sequences is impossible. In the outlook I consider two alternative approaches: (i) justification externalism and (ii) optimality justifications.

Copyright

Corresponding author

References

Hide All
Barnett, Z. and Li, H. 2018. ‘Fool Me Once: Can Indifference Vindicate Induction?Episteme, 15(2): 202–8.
Blackburn, S. (ed.) 2016. The Oxford Dictionary of Philosophy, 3rd edition. Oxford: Oxford University Press.
Cariani, F. 2015. ‘Some Questions about the Problem of the Problem of Induction.’ Episteme, 12(2): 291–6.
Carnap, R. 1950. Logical Foundations of Probability. Chicago, IL: University of Chicago Press.
Giraud-Carrier, C. and Provost, F. 2005. ‘Toward a Justification of Meta-learning: Is the No Free Lunch Theorem a Show-stopper?’ In Workshop on Meta-learning (Proceedings of the ICML 2005), pp. 1219. Burlington, MA: Morgan Kaufmann.
Howson, C. and Urbach, P. 1996. Scientific Reasoning: The Bayesian Approach, 2nd edition. Chicago, IL: Open Court.
Kelly, K.T. 1996. The Logic of Reliable Inquiry. New York, NY: Oxford University Press.
Martignon, L. and Hoffrage, U. 1999. ‘Why Does One-Reason Decision Making Work?’ In G., Gigerenzer, P.M., Todd and the ABC Research Group (eds), Simple Heuristics That Make Us Smart, pp. 119–40. Oxford: Oxford University Press.
Putnam, H. 1965. ‘Trial and Error Predicates and a Solution to a Problem of Mostowski.’ Journal of Symbolic Logic, 30: 4957.
Reichenbach, H. 1949. The Theory of Probability. Berkeley, CA: University of California Press.
Schaffer, C. 1994. ‘A Conservation Law for Generalization Performance.’ In Cohen, W.W. and Hirsh, H. (eds), Machine Learning (Proceedings of ICML 1994), pp. 259–65. Burlington, MA: Morgan Kaufmann.
Schurz, G. 2008. ‘The Meta-Inductivist's Winning Strategy in the Prediction Game: A New Approach to Hume's Problem.’ Philosophy of Science, 75: 278305.
Schurz, G. 2009. ‘Meta-Induction and Social Epistemology.Episteme, 6: 200–20.
Schurz, G. 2017. ‘No Free Lunch Theorem, Inductive Skepticism, and the Optimality of Meta-Induction.Philosophy of Science, 84: 825–39.
Schurz, G. 2019. Hume's Problem Solved: The Optimality of Meta-Induction. Cambridge, MA: MIT Press.
Solomonoff, R.J. 1964. ‘A Formal Theory of Inductive Inference.Information and Control, 7: 122 (part I), 224–54 (part II).
van Cleve, J. 1984. ‘Reliability, Justification, and Induction.’ Midwest Studies in Philosophy, 9(1): 555–67.
van Cleve, J. 2003. ‘Is Knowledge Easy – or Impossible? Externalism as the Only Alternative to Skepticism.’ In Luper, S. (ed.), The Skeptics: Contemporary Essays, pp. 4559. Aldershot: Ashgate.
White, R. 2015. ‘The Problem of the Problem of Induction.’ Episteme, 12(2): 275–90.
Wolpert, D.H. 1992. ‘On the Connection between In-Sample Testing and Generalization Error.’ Complex Systems, 6: 4794.
Wolpert, D.H. 1996. ‘The Lack of A Priori Distinctions between Learning Algorithms.’ Neural Computation, 8(7): 1341–90.

THE NO FREE LUNCH THEOREM: BAD NEWS FOR (WHITE'S ACCOUNT OF) THE PROBLEM OF INDUCTION

  • Gerhard Schurz

Metrics

Full text views

Total number of HTML views: 0
Total number of PDF views: 0 *
Loading metrics...

Abstract views

Total abstract views: 0 *
Loading metrics...

* Views captured on Cambridge Core between <date>. This data will be updated every 24 hours.

Usage data cannot currently be displayed