Skip to main content

A Priori Advantages of Meta-Induction and the No Free Lunch Theorem: A Contradiction?

  • Conference paper
  • First Online:
KI 2017: Advances in Artificial Intelligence (KI 2017)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 10505))

Abstract

Recently a new account to the problem of induction has been developed [1], based on a priori advantages of regret-weighted meta-induction (RW) in online learning [2]. The claimed a priori advantages seem to contradict the no free lunch (NFL) theorem, which asserts that relative to a state-uniform prior distribution (SUPD) over possible worlds all (non-clairvoyant) prediction methods have the same expected predictive success. In this paper we propose a solution to this problem based on four novel results:

  • RW enjoys free lunches, i.e., its predictive long-run success dominates that of other prediction strategies.

  • Yet the NFL theorem applies to online prediction tasks provided the prior distribution is a SUPD.

  • The SUPD is maximally induction-hostile and assigns a probability of zero to all possible worlds in which RW enjoys free lunches. This dissolves the apparent conflict with the NFL.

  • The a priori advantages of RW can be demonstrated even under the assumption of a SUPD. Further advantages become apparent when a frequency-uniform distribution is considered.

This work was supported by the DFG (Deutsche Forschungsgemeinschaft), SPP 1516. For valuable help we are indebted to Ronald Ortner.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 39.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Notes

  1. 1.

    Cf. [6, Sect. 4] and [7, Sect. 3], citing statements from a 1994 e-mail discussion.

  2. 2.

    [8] mentions the weak no free lunch theorem in a small paragraph on p. 1354; for our purpose this NFL theorem is the most important one.

References

  1. Schurz, G.: The meta-inductivist’s winning strategy in the prediction game: a new approach to Hume’s problem. Philos. Sci. 75, 278–305 (2008)

    Article  MathSciNet  Google Scholar 

  2. Cesa-Bianchi, N., Lugosi, G.: Prediction, Learning, and Games. Cambridge University Press, Cambridge (2006)

    Book  MATH  Google Scholar 

  3. Wolpert, D., Macready, W.: No free lunch theorems for search. Technical report SFI-TR-95-02-010, Santa Fe Institute (1995)

    Google Scholar 

  4. Wolpert, D.: On the connection between in-sample testing and generalization error. Complex Syst. 6, 47–94 (1992)

    MathSciNet  MATH  Google Scholar 

  5. Schaffer, C.: A conservation law for generalization performance. In: Machine Learning (Proceedings of ICML 1994), pp. 259–265. Morgan Kaufmann, Burlington (1994)

    Google Scholar 

  6. Rao, R., Gordon, D., Spears, W.: For every generalization action, is there really an equal and opposite reaction? In: Machine Learning (Proceedings of ICML 1995), pp. 471–479. Morgan Kaufmann, Burlington (1994)

    Google Scholar 

  7. Giraud-Carrier, C., Provost, F.: Toward a justification of meta-learning: is the no free lunch theorem a show-stopper? In: Proceedings of the ICML-2005 Workshop on Meta-learning, pp. 12–19 (2006)

    Google Scholar 

  8. Wolpert, D.: The lack of a priori distinctions between learning algorithms. Neural Comput. 8, 1341–1390 (1996)

    Article  Google Scholar 

  9. Schurz, G., Thorn, P.: The revenge of ecological rationality: strategy-selection by meta-induction. Minds Mach. 26(1), 31–59 (2016)

    Article  Google Scholar 

  10. Schurz, G.: Meta-induction is an optimal prediction strategy. In: Proceedings of the 18th Annual Belgian-Dutch Conference on Machine Learning, pp. 66–74. University of Tilburg (2009)

    Google Scholar 

  11. Gigerenzer, G., Todd, P.M., the ABC Research Group. (eds.): Simple Heuristics That Make Us Smart. Oxford University Press, Dordrecht (1999)

    Google Scholar 

  12. Schurz, G.: The Optimality of Meta-induction. A New Approach to Hume’s Problem. Book manuscript (2017)

    Google Scholar 

  13. Carnap, R.: Logical Foundations of Probability, 2nd edn. University of Chicago Press, Chicago (1962)

    MATH  Google Scholar 

  14. Howson, C., Urbach, P.: Scientific Reasoning: The Bayesian Approach, 2nd edn. Open Court, Chicago (1996)

    Google Scholar 

  15. Solomonoff, R.: A formal theory of inductive inference. Inf. Control 7(1–22), 224–254 (1964)

    Article  MathSciNet  MATH  Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Gerhard Schurz .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2017 Springer International Publishing AG

About this paper

Cite this paper

Schurz, G., Thorn, P. (2017). A Priori Advantages of Meta-Induction and the No Free Lunch Theorem: A Contradiction?. In: Kern-Isberner, G., Fürnkranz, J., Thimm, M. (eds) KI 2017: Advances in Artificial Intelligence. KI 2017. Lecture Notes in Computer Science(), vol 10505. Springer, Cham. https://doi.org/10.1007/978-3-319-67190-1_18

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-67190-1_18

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-67189-5

  • Online ISBN: 978-3-319-67190-1

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics