Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Skip to main content
Springer Nature Link
Log in

Learnability of Quantified Formulas

  • Conference paper
  • First Online:
Computational Learning Theory (EuroCOLT 1999)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 1572))

Included in the following conference series:

  • 670 Accesses

Abstract

We consider the following classes of quantified formulas. Fix a set of basic relations called a basis. Take conjunctions of these basic relations applied to variables and constants in arbitrary ways. Finally, quantify existentially or universally some of the variables. We introduce some conditions on the basis that guarantee efficient learnability. Furthermore, we show that with certain restrictions on the basis the classification is complete. We introduce, as an intermediate tool, a link between this class of quantified formulas and some well-studied structures in Universal Algebra called clones. More precisely, we prove that the computational complexity of the learnability of these formulas is completely determined by a simple algebraic property of the basis of relations, their clone of polymorphisms. Finally, we use this technique to give a simpler proof of the already known dichotomy theorem over boolean domains and we present an extension of this theorem to bases with infinite size.

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

Access this chapter

Log in via an institution

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Similar content being viewed by others

References

  1. D. Angluin. Queries and Concept Learning. Machine Learning, 2:319–342, 1988.

    Google Scholar 

  2. D. Angluin, M. Frazier, and L. Pitt. Learning Conjunctions of Horn Clauses. Machine Learning, 9:147–164, 1992.

    MATH  Google Scholar 

  3. D. Angluin and M. Kharitonov. When won’t Membership Queries help. Journal of Computer and System Sciences, 50:336–355, 1995.

    Article  MATH  MathSciNet  Google Scholar 

  4. K.A. Baker and A.F. Pixley. Polynomial Interpolation and the Chinese Remainder Theorem for Algebraic Systems. Math. Z., 1975.

    Google Scholar 

  5. N.H. Bshouty. Exact learning boolean functions via the monotone theory. Information and Computation, pages 146–153, November 1995.

    Google Scholar 

  6. Zhixiang Chen and Steven Homer. Learning counting functions with queries. Theoretical Computer Science, 180(1–2):155–168, 10 June 1997.

    Article  MATH  MathSciNet  Google Scholar 

  7. V. Dalmau. A Dichotomy Theorem for Learning Quantified Boolean Formulas. In 10th Annual ACM Conference on Computational Learning Theory COLT’97, pages 193–200, 1997.

    Google Scholar 

  8. V. Dalmau and P. Jeavons. Learnability of Quantified Formulas. Technical Report CSD-TR-98-10, Royal Holloway, University of London, UK, 1998.

    Google Scholar 

  9. T. Feder and M.Y. Vardi. The Computational Structure of Monotone Monadic SNP and Contraint Satisfaction: A Study through Datalog and Group Theory. SIAM J. Computing, 28(1):57–104, 1998.

    Article  MATH  MathSciNet  Google Scholar 

  10. D. Helmbold, R. Sloan, and M. Warmuth. Learning Nested Differences of Intersection-Closed Concept Classes. Machine Learning, 5(2):165–196, 1990.

    Google Scholar 

  11. M.C. Hoffmann. Group-Theoretic Algorithms and Graph Isomorphism, volume 136 of Lecture Notes in Computer Science. Springer-Verlag, 1982.

    MATH  Google Scholar 

  12. Jeffrey C. Jackson. An Efficient Membership-query Algorithm for Learning DNF with respect to the Uniform Distribution. Journal of Computer and System Sciences, 55(3):414–440, December 1997.

    Article  MATH  MathSciNet  Google Scholar 

  13. P. Jeavons, D. Cohen, and M.C. Cooper. Constraints, Consistency and Closure. Artificial Intelligence, 101:251–265, 1988.

    Article  MathSciNet  Google Scholar 

  14. P. Jeavons, D. Cohen, and M. Gyssens. A Unifying Framework for Tractable Constraints. In 1st International Conference on Principles and Practice of Constraint Programming, CP’95, Cassis (France), September 1995, volume 976 of Lecture Notes in Computer Science, pages 276–291. Springer-Verlag, 1995.

    Google Scholar 

  15. P. Jeavons, D. Cohen, and M. Gyssens. Closure Properties of Constraints. Journal of the ACM, 44(4):527–548, July 1997.

    Article  MATH  MathSciNet  Google Scholar 

  16. P. Jeavons and M. Cooper. Tractable Constraints on Ordered Domains. Artificial Intelligence, 79:327–339, 1996.

    Article  MathSciNet  Google Scholar 

  17. Michael Kearns and Leslie Valiant. Cryptographic limitations on learning Boolean formulae and finite automata. Journal of the ACM, 41(1):67–95, January 1994.

    Article  MATH  MathSciNet  Google Scholar 

  18. W. Maass and G. Turán. On Learnability and Predicate Logic. In Bar-Ilan Symposium onf the Foundations of Artificial Intelligence, BISFAI’95, pages 75–85, 1995.

    Google Scholar 

  19. R.N. McKenzie, G.F. McNulty, and W.F. Taylor. Algebras, Lattices and Varieties, volume 1. Wadsworth and Brooks, 1987.

    Google Scholar 

  20. S. Muggleton, editor. Inductive Logic Programming. Academic Press, 1992.

    Google Scholar 

  21. S. Muggleton and L. De Raedt. Inductive Logic Programming: Theory and Methods. Journal of Logic Programming, 19/20:7:629–679, 1994.

    Article  Google Scholar 

  22. B.K. Natarajan. On Learning Boolean Functions. In 9thAnnual ACM Symposium on Theory of Computing, STOC’87, pages 296–304, 1987.

    Google Scholar 

  23. N. Pippenger. Theories of Computability. Cambridge University Press, 1997.

    Google Scholar 

  24. E.L. Post. The Two-Valued Iterative Systems of Mathematical Logic, volume 5 of Annals of Mathematics Studies. Princeton, N.J, 1941.

    Google Scholar 

  25. T.J. Schaefer. The Complexity of Satisfiability Problems. In 10th Annual ACM Symposium on Theory of Computing, pages 216–226, 1978.

    Google Scholar 

  26. A. Szendrei. Clones in Universal Algebra, volume 99 of Seminaires de Mathématiques Supéreiores. University of Montreal, 1986.

    Google Scholar 

  27. L. Valiant. A Theory of the Learnable. Comm. ACM, 27(11):1134–1142, 1984.

    Article  MATH  Google Scholar 

  28. Yu.I. Yanov and A.A. Muchnik. On the existence of k-valued closed classes without a finite basis. Dokl. Akad. Nauk SSSR, 127:44–46, 1959. In russian.

    MATH  MathSciNet  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Departament LSI, Universitat Politécnica de Catalunya, Barcelona, Spain

    Víctor Dalmau

  2. Department of Computer Science, Royal Holloway, University of London, London, UK

    Peter Jeavons

Authors
  1. Víctor Dalmau
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Peter Jeavons
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. Lehrstuhl für Informatik II, Universität Dortmund, D-44221, Dortmund, Germany

    Paul Fischer

  2. Fakultät für Mathematik, Ruhr Universität Bochum, D-44780, Bochum, Germany

    Hans Ulrich Simon

Rights and permissions

Reprints and permissions

Copyright information

© 1999 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Dalmau, V., Jeavons, P. (1999). Learnability of Quantified Formulas. In: Fischer, P., Simon, H.U. (eds) Computational Learning Theory. EuroCOLT 1999. Lecture Notes in Computer Science(), vol 1572. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-49097-3_6

Download citation

  • DOI: https://doi.org/10.1007/3-540-49097-3_6

  • Published:

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-65701-9

  • Online ISBN: 978-3-540-49097-5

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics

Search

Navigation