Abstract
This paper studies the query complexity of learning classes of expressions in propositional logic from equivalence and membership queries. We give new constructions of polynomial size certificates of non-membership for monotone, unate and Horn CNF functions. Our constructions yield quantitatively different bounds from previous constructions of certificates for these classes. We prove lower bounds on certificate size which show that for some parameter settings the certificates we construct for these classes are exactly optimal. Finally, we also prove that a natural generalization of these classes, the class of renamable Horn CNF functions, does not have polynomial size certificates of non-membership, thus answering an open question of Feigelson.
This work has been partly supported by NSF Grant IIS-0099446 (M.A. and R.K.) and by an NSF Mathematical Sciences Postdoctoral Research Fellowship (R.S). Work done while R.S. was at the Division of Engineering and Applied Sciences, Harvard University.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Angluin, D.: Queries and concept learning. Machine Learning 2(4), 319–342 (1988)
Angluin, D., Frazier, M., Pitt, L.: Learning conjunctions of Horn clauses. Machine Learning 9, 147–164 (1992)
Angluin, D.: Queries revisited. In: Abe, N., Khardon, R., Zeugmann, T. (eds.) ALT 2001. LNCS (LNAI), vol. 2225, pp. 12–31. Springer, Heidelberg (2001)
Arias, M., Khardon, R.: Learning closed horn expressions. Information and Computation, 214–240 (2002)
Arimura, H.: Learning acyclic first-order Horn sentences from entailment. In: Li, M. (ed.) ALT 1997. LNCS(LNAI), vol. 1316. Springer, Heidelberg (1997)
Balcázar, J.L., Castro, J., Guijarro, D.: The consistency dimension and distribution-dependent learning from queries. In: Nadathur, G. (ed.) PPDP 1999. LNCS(LNAI), vol. 1702. Springer, Heidelberg (1999)
Bshouty, N.H.: Simple learning algorithms using divide and conquer. In: Proceedings of the Conference on COLT (1995)
De Raedt, L.: Logical settings for concept learning. Artificial Intelligence 95(1), 187–201 (1997), . See also relevant Errata (forthcoming)
Feigelson, A.: On boolean functions and their orientations: Learning, monotone dimension and certificates. Ph.D. Thesis, Northwestern University, Department of Electrical and Computer Engineering (1998)
Feigelson, A., Hellerstein, L.: Conjunctions of unate DNF formulas: Learning and structure. Information and Computation 140(2), 203–228 (1988)
Frazier, M., Pitt, L.: Learning from entailment: An application to propositional Horn sentences. In: Proceedings of the International Conference on Machine Learning, Amherst, MA, pp. 120–127. Morgan Kaufmann, San Francisco (1993)
Hegedus, T.: On generalized teaching dimensions and the query complexity of learning. In: Proceedings of the 8th Annual Conference on Computational Learning Theory (COLT 1995), New York, NY, USA, pp. 108–117. ACM Press, New York (1995)
Hellerstein, L.: On generalized constraints and certificates. Discrete Mathematics 226, 211–232 (2001)
Hellerstein, L., Pillaipakkamnatt, K., Raghavan, V., Wilkins, D.: How many queries are needed to learn? Journal of the ACM 43(5), 840–862 (1996)
Hellerstein, L., Raghavan, V.: Exact learning of DNF formulas using DNF hypotheses. In: Proceedings of the 34th Annual ACM Symposium on Theory of Computing (STOC 2002), New York, May 19–21, pp. 465–473. ACM Press, New York (2002)
Horn, A.: On sentences which are true of direct unions of algebras. Journal of Symbolic Logic 16, 14–21 (1956)
Khardon, R.: Learning function free Horn expressions. Machine Learning 37, 241–275 (1999)
Khardon, R., Roth, D.: Learning to reason with a restricted view. Machine Learning 35(2), 95–117 (1999)
Khardon, R., Roth, D.: Reasoning with models. Artificial Intelligence 87(1– 2), 187–213 (1996)
Littlestone, N.: Learning quickly when irrelevant attributes abound: A new linearthreshold algorithm. Machine Learning 2, 285–318 (1988)
Maass, W., Turán, G.: Lower bound methods and separation results for on-line learning models. Machine Learning 9, 107–145 (1992)
McKinsey, J.C.C.: The decision problem for some classes of sentences without quantifiers. J. Symbolic Logic 8, 61–76 (1943)
Pillaipakkamnatt, K., Raghavan, V.: On the limits of proper learnability of subclasses of DNF formulas. Machine Learning 25, 237 (1996)
Reddy, C., Tadepalli, P.: Learning Horn definitions with equivalence and membership queries. In: Džeroski, S., Lavrač, N. (eds.) ILP 1997. LNCS (LNAI), vol. 1297, pp. 243–255. Springer, Heidelberg (1997)
Reddy, C., Tadepalli, P.: Learning first order acyclic Horn programs from entailment. In: Page, D.L. (ed.) ILP 1998. LNCS (LNAI), vol. 1446, pp. 23–37. Springer, Heidelberg (1998)
Valiant, L.G.: A theory of the learnable. Communications of the ACM 27(11), 1134–1142 (1984)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Arias, M., Khardon, R., Servedio, R.A. (2003). Polynomial Certificates for Propositional Classes. In: Schölkopf, B., Warmuth, M.K. (eds) Learning Theory and Kernel Machines. Lecture Notes in Computer Science(), vol 2777. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-45167-9_39
Download citation
DOI: https://doi.org/10.1007/978-3-540-45167-9_39
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-40720-1
Online ISBN: 978-3-540-45167-9
eBook Packages: Springer Book Archive