Abstract
We consider the following classes of quantified boolean formulas. Fix a finite set of basic boolean functions. Take conjunctions of these basic functions applied to variables and constants in arbitrary ways. Finally quantify existentially or universally some of the variables. We prove the following dichotomy theorem: For any set of basic boolean functions, the resulting set of formulas is either polynomially learnable from equivalence queries alone or else it is not PAC-predictable even with membership queries under cryptographic assumptions. Furthermore, we identify precisely which sets of basic functions are in which of the two cases.
Article PDF
Similar content being viewed by others
Avoid common mistakes on your manuscript.
References
Angluin, D. (1988). Queries and concept learning. Machine Learning, 2, 319–342.
Angluin, D., Frazier, M., & Pitt, L. (1992). Learning conjunctions of horn clauses. Machine Learning, 9, 147–164.
Angluin, D., & Kharitonov, M. (1995). When won't membership queries help? Journal of Computer and System Sciences, 50, 336–355.
Berggren, U. (1993). Linear time deterministic learning of k-term DNF. Proc. 6th Annual Workshop on Computational Learning Theory (pp. 37–40).
Chen, Z., & Homer, S. (1997). Learning counting functions with queries. Theoretical Computer Science, 180, 155–168.
Creignou, N. (1995). Adichotomy theorem for maximum generalized satisfiability problems. Journal of Computer and System Sciences, 51(3), 511–522.
Creignou, N., & Hermann, M. (1996). Complexity of generalized satisfiability counting problems. Information and Computation, 125, 1–12.
Dalmau, V. (1997). Some dichotomy theorems on constant-free quantified boolean formulas (Technical Report LSI-97-43-R), Department LSI, Universitat Politécnica de Catalunya.
Dor, D., & Tarsi, M. (1997). Graph decomposition is NP-complete: A complete proof of Holyer's conjecture. SIAM Journal on Computing, 26(4), 1166–1187.
Fortune, S., Hopcroft, J., & Wyllie, J. (1980). The directed subgraph homeomorphism problem. Theor. Comp. Sci., 81(2), 111–121.
Greenlaw, R., Hoover, H.J., & Ruzzo, W.L. (1995). Limits to Parallel Computation: P-completeness theory. Oxford University Press.
Hell, P., & Nešetřil, N. (1990). On the complexity of H-coloring. J. Combin. Theory Ser. B, 48, 92–110.
Kavvadias, D., & Sidderi, M. (1996). The inverse satisfiability problem. Proc. 2nd Annual International Conference on Computing and Combinatorics, COCOON'96 (pp. 250–259).
Kearns, M., & Valiant, L. (1994). Cryptographic limitations on learning boolean formulae and finite automata. J. ACM, 41(1), 67–95.
Khanna, S., Sudan, M., & Trevisan, L. (1997). Constraint satisfaction: The approximability of minimization problems. Proc. of the 12th IEEE Conference on Computational Complexity.
Khanna, S., Sudan, M., & Williamson, P. (1997). A complete classification of the approximability of maximization problems derived from boolean constraint satisfaction. Proc. of the 29th Annual ACM Symposium on the Theory of Computing.
Maass W., & Turán, G. (1995). On learnability and predicate logic. Proc. Bar-Ilan Symposium on the Foundations of Artificial Intelligence, BISFAI'95 (pp. 75–85).
Papadimitriou, C.H. (1994). Computational Complexity. Addison-Wesley.
Pitt, L., & Warmuth, M. (1990). Prediction preserving reducibility. Journal of Computer and System Sciences, 41, 430–467.
Schaefer, T.J. (1978). The complexity of satisfiability problems. Proc. 10th Annual ACM Symposium on Theory of Computing (pp. 216–226).
Valiant, L. (1984). A theory of the learnable. Comm. ACM, 27, 1134–1142.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Dalmau, V. A Dichotomy Theorem for Learning Quantified Boolean Formulas. Machine Learning 35, 207–224 (1999). https://doi.org/10.1023/A:1007582729656
Issue Date:
DOI: https://doi.org/10.1023/A:1007582729656