Advertisement

Is There an Elegant Universal Theory of Prediction?

  • Shane Legg
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4264)

Abstract

Solomonoff’s inductive learning model is a powerful, universal and highly elegant theory of sequence prediction. Its critical flaw is that it is incomputable and thus cannot be used in practice. It is sometimes suggested that it may still be useful to help guide the development of very general and powerful theories of prediction which are computable. In this paper it is shown that although powerful algorithms exist, they are necessarily highly complex. This alone makes their theoretical analysis problematic, however it is further shown that beyond a moderate level of complexity the analysis runs into the deeper problem of Gödel incompleteness. This limits the power of mathematics to analyse and study prediction algorithms, and indeed intelligent systems in general.

Keywords

Prediction Algorithm Kolmogorov Complexity Input String Computable Sequence Short Program 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Barzdin, J.M.: Prognostication of automata and functions. Information Processing 71, 81–84 (1972)MathSciNetGoogle Scholar
  2. 2.
    Calude, C.S.: Information and Randomness, 2nd edn. Springer, Berlin (2002)MATHGoogle Scholar
  3. 3.
    Chaitin, G.J.: Gödel’s theorem and information. International Journal of Theoretical Physics 22, 941–954 (1982)CrossRefMathSciNetGoogle Scholar
  4. 4.
    Dawid, A.P.: Comment on The impossibility of inductive inference. Journal of the American Statistical Association 80(390), 340–341 (1985)CrossRefMathSciNetGoogle Scholar
  5. 5.
    Feder, M., Merhav, N., Gutman, M.: Universal prediction of individual sequences. IEEE Trans. on Information Theory 38, 1258–1270 (1992)MATHCrossRefMathSciNetGoogle Scholar
  6. 6.
    Gödel, K.: Über formal unentscheidbare Sätze der principia mathematica und verwandter systeme I. Monatshefte für Matematik und Physik 38, 173–198 (1931); English translation by Mendelsohn, E.: On undecidable propositions of formal mathematical systems. In: Davis, M. (ed.) The undecidable, New York, pp. 39–71. Raven Press, Hewlitt (1965) Google Scholar
  7. 7.
    Mark Gold, E.: Language identification in the limit. Information and Control 10(5), 447–474 (1967)MATHCrossRefGoogle Scholar
  8. 8.
    Hutter, M.: Universal Artificial Intelligence: Sequential Decisions based on Algorithmic Probability, p. 300. Springer, Berlin (2005), http://www.idsia.ch/~marcus/ai/uaibook.htm MATHGoogle Scholar
  9. 9.
    Hutter, M.: On the foundations of universal sequence prediction. In: Cai, J.-Y., Cooper, S.B., Li, A. (eds.) TAMC 2006. LNCS, vol. 3959, pp. 408–420. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  10. 10.
    Li, M., Vitányi, P.M.B.: An introduction to Kolmogorov complexity and its applications, 2nd edn. Springer, Heidelberg (1997)MATHGoogle Scholar
  11. 11.
    Poland, J., Hutter, M.: Convergence of discrete MDL for sequential prediction. In: Shawe-Taylor, J., Singer, Y. (eds.) COLT 2004. LNCS (LNAI), vol. 3120, pp. 300–314. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  12. 12.
    Rissanen, J.J.: Fisher Information and Stochastic Complexity. IEEE Trans. on Information Theory 42(1), 40–47 (1996)MATHCrossRefMathSciNetGoogle Scholar
  13. 13.
    Solomonoff, R.J.: A formal theory of inductive inference: Part 1 and 2. Inform. Control 7(1–22), 224–254 (1964)MATHCrossRefMathSciNetGoogle Scholar
  14. 14.
    Solomonoff, R.J.: Complexity-based induction systems: comparisons and convergence theorems. IEEE Trans. Information Theory IT-24, 422–432 (1978)MATHCrossRefMathSciNetGoogle Scholar
  15. 15.
    Sutton, R., Barto, A.: Reinforcement learning: An introduction. MIT Press, Cambridge, MA (1998)Google Scholar
  16. 16.
    V’yugin, V.V.: Non-stochastic infinite and finite sequences. Theoretical computer science 207, 363–382 (1998)MATHCrossRefMathSciNetGoogle Scholar
  17. 17.
    Wallace, C.S., Boulton, D.M.: An information measure for classification. Computer Jrnl. 11(2), 185–194 (1968)MATHGoogle Scholar
  18. 18.
    Willems, F.M.J., Shtarkov, Y.M., Tjalkens, T.J.: The context-tree weighting method: Basic properties. IEEE Transactions on Information Theory 41(3) (1995)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Shane Legg
    • 1
  1. 1.Dalle Molle Institute for Artificial IntelligenceManno-LuganoSwitzerland

Personalised recommendations