Projective DNF Formulae and Their Revision

  • Robert H. Sloan
  • Balázs Szörényi
  • György Turán
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2777)


Valiant argued that biology imposes various constraints on learnability, and, motivated by these constraints, introduced his model of projection learning [14]. Projection learning aims to learn a target concept over some large domain, in this paper {0,1} n , by learning some of its projections to a class of smaller domains, and combining these projections. Valiant proved a general mistake bound for the resulting algorithm under certain conditions. The basic assumption underlying projection learning is that there is a family of simple projections that cover all positive instances of the target, where simple means belonging to some efficiently learnable class. The projections describing the target in this way can also be thought of as a set of experts, each specialized to classify a subset of the instances, such that whenever two experts overlap they always agree in their classification.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Angluin, D.: Queries revisited. In: Abe, N., Khardon, R., Zeugmann, T. (eds.) ALT 2001. LNCS (LNAI), vol. 2225, pp. 12–31. Springer, Heidelberg (2001)CrossRefGoogle Scholar
  2. 2.
    Auer, P., Warmuth, M.K.: Tracking the best disjunction. Machine Learning 32(2), 127–150 (1998); Earlier version in 36th FOCS (1995)Google Scholar
  3. 3.
    Blum, A.: On-line algorithms in machine learning (1996), Available from
  4. 4.
    Goldsmith, J., Sloan, R.H., Szörényi, B., Turán, G.: Theory revision with queries: Horn, read-once, and parity formulas. Technical Report TR03-039, Electronic Colloquium on Computational Complexity (ECCC) (2003) (Also submitted for journal publication), Available at Scholar
  5. 5.
    Goldsmith, J., Sloan, R.H., Turán, G.: Theory revision with queries: DNF formulas. Machine Learning 47(2/3), 257–295 (2002)MATHCrossRefGoogle Scholar
  6. 6.
    Hegedüs, T.: Generalized teaching dimensions and the query complexity of learning. In: Proc. 8th Annu. Conf. on Comput. Learning Theory, pp. 108–117. ACM Press, New York (1995)CrossRefGoogle Scholar
  7. 7.
    Hellerstein, L., Pillaipakkamnatt, K., Raghavan, V., Wilkins, D.: How many queries are needed to learn? J. ACM 43(5), 840–862 (1996)MATHCrossRefMathSciNetGoogle Scholar
  8. 8.
    Helmbold, D., Sloan, R., Warmuth, M.K.: Learning nested differences of intersection closed concept classes. Machine Learning 5(2), 165–196 (1990); Special Issue on Computational Learning Theory, first appeared in 2nd COLT conference (1989)Google Scholar
  9. 9.
    Kivinen, J., Warmuth, M.K.: Additive versus exponentiated gradient updates for linear prediction. In: Proc. 27th Annual ACM Symposium on Theory of Computing, pp. 209–218. ACM Press, New York (1995)Google Scholar
  10. 10.
    Littlestone, N.: Learning quickly when irrelevant attributes abound: A new linearthreshold algorithm. Machine Learning 2(4), 285–318 (1988)Google Scholar
  11. 11.
    Littlestone, N.: A mistake-bound version of Rivest’s decision-list algorithm. Personal communication to Avrim Blum (1989)Google Scholar
  12. 12.
    Mesterharm, C.: Tracking linear-threshold concepts with Winnow. In: Kivinen, J., Sloan, R.H. (eds.) COLT 2002. LNCS (LNAI), vol. 2375, pp. 138–152. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  13. 13.
    Rivest, R.L.: Learning decision lists. Machine Learning 2, 229–246 (1987)MathSciNetGoogle Scholar
  14. 14.
    Valiant, L.G.: Projection learning. Machine Learning 37(2), 115–130 (1999)MATHCrossRefGoogle Scholar
  15. 15.
    Valiant, L.G.: A neuroidal architecture for cognitive computation. Journal of the ACM 47(5), 854–882 (2000)CrossRefMathSciNetGoogle Scholar
  16. 16.
    Wrobel, S.: Concept Formation and Knowledge Revision. Kluwer, Dordrecht (1994)MATHGoogle Scholar
  17. 17.
    Wrobel, S.: First order theory refinement. In: De Raedt, L. (ed.) Advances in ILP, pp. 14–33. IOS Press, Amsterdam (1995)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Robert H. Sloan
    • 1
  • Balázs Szörényi
    • 2
  • György Turán
    • 3
  1. 1.U. of Illinois at Chicago 
  2. 2.U. of SzegedHungary
  3. 3.U. of Illinois at Chicago and RGAI Hungarian Academy of Sciences 

Personalised recommendations