Exact learning of subclasses of CDNF formulas with membership queries

  • Carlos Domingo
Session 5
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1090)


We consider the exact, learuability of subclasses of Boolean formulas from membership queries alone. We show how to combine known learning algorithms that use membership and equivalence queries to obtain new learning results only with memberships. In particular we show the exact learuability of read-k monotone formulas, Sat-k\(\mathcal{O}\)(log n)-CDNF, and \(\mathcal{O}(\sqrt {\log n} )\)-size CDNF from membership queries only.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [AHP92]
    H. Aizenstein, L. Hellerstein, and L. Pitt. R.ead-thrice DNF is hard to learn with membership queries and equivalence queries. Proceedings of the. 33rd Annual IEEE Symposium on Foundations of Computer Science, (1992), 523–532.Google Scholar
  2. [AP91]
    H. Aizeustein, and L. Pitt. Exact, learning of read-twice DNF formulas. Proceedings of the 32nd Annual IEEE Symposium on Foundations of Computer Science, (1991), 170–179.Google Scholar
  3. [Ang88]
    D. Angluin. Queries and Concept Learning. Machine Learning, 2, (1988), 319–342.Google Scholar
  4. [AHK93]
    D. Angluin, L. Hellerstein, and M. Karpinski. Learning read-once formulas with queries. Journal of the Association for Computing Machinery, 40, (1993), 185–210.Google Scholar
  5. [AK91]
    D. Augluin, and M. Kharitouov. When won't membership queries help? Proceedings of the 23rd ACM Symposium on the Theory of Computing, (1991), 444–454.Google Scholar
  6. [BI94]
    J.C. Bioch, and T. Ibaraki. Complexity of Identification and Dualization of Positive Boolean Functions. Information, and Computation, 123, (1995), 50–63.Google Scholar
  7. [BF+94]
    A. Blum, M. Furst, J. Jackson, M. Kearns, Y. Mausonr, and S. Rudich. Weakly learning DNF and characterizing statistical query learning using Fourier analysis. Proceedings of the 26th. ACM Symposium on the Theory of Computing, (1994), 382–389.Google Scholar
  8. [Bsh95]
    N.H. Bshouty. Exact Learning Boolean functions via the Monotone Theory. Information and Computation, 123, (1195), 146–53.Google Scholar
  9. [BC+95]
    N.H. Bshouty, R. Cleve, R. Gavaldà. S. Kannau, and C. Tamon. Oracles and Queries that are Sufficient for Exact, Learning. Electronic Colloquium on Complexity. Technical Report TR95-015, 1995.Google Scholar
  10. [BGHM93]
    N.H. Bshouty, S.A. Goldman, T. Hancock, and S. Matar. Asking Queries to Minimize Errors. Proceedings of the 6th Workshop on Computational Learning Theory, (1993), 41–50.Google Scholar
  11. [Jac94]
    J. Jackson. An Efficient Membership-Query Algorithm for Learning DNF with Respect to the Uniform Distribution. Proceedings of the 35th Annual IEEE Symposium on Foundations of Computer Science, (1994), 42–53.Google Scholar
  12. [KM93]
    E. Kushilevitz, and Y. Mansonr. Learning decision trees using the Fourier spectrum. SIAM Journal on Computing. 22, (1993), 1331–1348.Google Scholar
  13. [MI94b]
    K. Makino. and T. Ibaraki. The Maximum Latency and Identification of Positive Boolean Functions. ISAAC'94. Algorithms and Computation, Lecture Notes in Computer Science, 834, (1994), 324–332.Google Scholar
  14. [PR95]
    K. Pillaipakkamnatt, and V. Raghavan. Read-Twice DNF Formulas are Properly Learnable. Information and-Computation, 122, (1995), 236–267.Google Scholar
  15. [Val84]
    L.G. Valiant. A theory of the learnable. Communications of the ACM, 27(11). (1984), 1134–1142.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1996

Authors and Affiliations

  • Carlos Domingo
    • 1
  1. 1.Dept. of Computer ScienceTokyo Institute of TechnologyTokyoJapan

Personalised recommendations