Advertisement

How Many Query Superpositions Are Needed to Learn?

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

Abstract

This paper introduces a framework for quantum exact learning via queries, the so-called quantum protocol. It is shown that usual protocols in the classical learning setting have quantum counterparts. A combinatorial notion, the general halving dimension, is also introduced. Given a quantum protocol and a target concept class, the general halving dimension provides lower and upper bounds on the number of queries that a quantum algorithm needs to learn. For usual protocols, the lower bound is also valid even if only involution oracle teachers are considered. Under some protocols, the quantum upper bound improves the classical one. The general halving dimension also approximates the query complexity of ordinary randomized learners. From these bounds we conclude that quantum devices can allow moderate improvements on the query complexity. However, any quantum polynomially query learnable concept class must be also polynomially learnable in the classical setting.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Ambainis, A.: Quantum lower bounds by quantum arguments. J. Comput. Syst. Sci. 64(4), 750–767 (2002)zbMATHCrossRefMathSciNetGoogle Scholar
  2. 2.
    Ambainis, A., Iwama, K., Kawachi, A., Masuda, H., Putra, R.H., Yamashita, S.: Quantum identification of boolean oracles. In: Diekert, V., Habib, M. (eds.) STACS 2004. LNCS, vol. 2996, pp. 105–116. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  3. 3.
    Angluin, D.: Queries and concept learning. Machine Learning 2, 319–342 (1988)Google Scholar
  4. 4.
    Atici, A., Servedio, R.A.: Improved bounds on quantum learning algorithms. Quantum Information Processing 4(5), 355–386 (2005)CrossRefMathSciNetGoogle Scholar
  5. 5.
    Balcázar, J.L., Castro, J., Guijarro, D.: A general dimension for exact learning. In: Helmbold, D.P., Williamson, B. (eds.) COLT 2001 and EuroCOLT 2001. LNCS (LNAI), vol. 2111, pp. 354–367. Springer, Heidelberg (2001)CrossRefGoogle Scholar
  6. 6.
    Balcázar, J.L., Castro, J., Guijarro, D.: A new abstract combinatorial dimension for exact learning via queries. J. Comput. Syst. Sci. 64(1), 2–21 (2002)zbMATHCrossRefGoogle Scholar
  7. 7.
    Beals, R., Buhrman, H., Cleve, R., Mosca, M., de Wolf, R.: Quantum lower bounds by polynomials. J. ACM 48(4), 778–797 (2001)zbMATHCrossRefMathSciNetGoogle Scholar
  8. 8.
    Bennett, C.H.: Logical reversibility of computation. IBM Journal of Research and Development 17, 525–532 (1973)zbMATHCrossRefGoogle Scholar
  9. 9.
    Bennett, C.H., Bernstein, E., Brassard, G., Vazirani, U.V.: Strengths and weaknesses of quantum computing. SIAM J. Comput. 26(5), 1510–1523 (1997)zbMATHCrossRefMathSciNetGoogle Scholar
  10. 10.
    Bernstein, E., Vazirani, U.V.: Quantum complexity theory. SIAM J. Comput. 26(5), 1411–1473 (1997)zbMATHCrossRefMathSciNetGoogle Scholar
  11. 11.
    Boyer, M., Brassard, G., Høyer, P., Tapp, A.: Tight bounds on quantum searching. Fortschritte der Physik 46(4-5), 493–505 (1998)CrossRefGoogle Scholar
  12. 12.
    Bshouty, N.H., Jackson, J.C.: Learning DNF over the uniform distribution using a quantum example oracle. SIAM Journal on Computing 28(3), 1136–1153 (1999)zbMATHCrossRefMathSciNetGoogle Scholar
  13. 13.
    Deutsch, D., Jozsa, R.: Rapid solution of problems by quantum computation. Proc. Roy. Soc. Lond. A 439, 553–558 (1992)zbMATHCrossRefMathSciNetGoogle Scholar
  14. 14.
    Grover, L.K.: A fast quantum mechanical algorithm for database search. In: STOC, pp. 212–219 (1996)Google Scholar
  15. 15.
    Hellerstein, L., Pillaipakkamnatt, K., Raghavan, V., Wilkins, D.: How many queries are needed to learn? Journal of the ACM 43(5), 840–862 (1996)zbMATHCrossRefMathSciNetGoogle Scholar
  16. 16.
    Hunziker, M., Meyer, D.A., Park, J., Pommersheim, J., Rothstein, M.: The geometry of quantum learning. arXiv:quant-ph/0309059 (to appear in Quantum Information Processing, 2003)Google Scholar
  17. 17.
    Servedio, R.A., Gortler, S.J.: Equivalences and separations between quantum and classical learnability. SIAM J. Comput. 33(5), 1067–1092 (2004)zbMATHCrossRefMathSciNetGoogle Scholar
  18. 18.
    Simon, D.R.: On the power of quantum computation. SIAM J. Comput. 26(5), 1474–1483 (1997)zbMATHCrossRefMathSciNetGoogle Scholar
  19. 19.
    Simon, H.U.: How many queries are needed to learn one bit of information? Annals of Mathematics and Artificial Intelligence 39, 333–343 (2003)zbMATHCrossRefMathSciNetGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Jorge Castro
    • 1
  1. 1.Software Department.Universitat Politècnica de CatalunyaBarcelonaSpain

Personalised recommendations