Abstract
In this paper we consider the complexity of learning monotone DNF formulae and Boolean circuits in an exact learning model called the teaching assistant model. This model, introduced in one of our earlier works, uses teaching assistant classes for classifying learning problems. Teaching assistant classes are a learning-theoretic analog of complexity classes. We show that monotone DNFs are learnable using a teaching assistant in the class SPP. On the other hand, Boolean circuits and general DNFs are not learnable using an SPP teaching assistant unless \(\mbox{\rm NP}\subseteq \mbox{\rm SPP}\). We also show that learnability of Boolean circuits with an assistant in the class NP will improve the Karp-Lipton collapse result to PNP.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Angluin, D.: Queries and concept learning. Machine Learning 2, 319–342 (1988)
Arvind, V., Kurur, P.: Graph isomorphism is in SPP. Proceedings of the 43rd Annual IEEE Symposium on Foundations of Computer Science, 743–750 (2002)
Arvind, V., Vinodchandran, N.V.: The complexity of exactly learning algebraic concepts. In: Arikawa, S., Sharma, A.K. (eds.) ALT 1996. LNCS, vol. 1160, pp. 100–112. Springer, Heidelberg (1996)
Arvind, V., Vinodchandran, N.V.: Exact learning via teaching assistants. Theoretical Computer Science 241, 51–81 (2000) (special issue devoted to the 7th International Workshop on Algorithmic Learning Theory)
Beigel, R.: Perceptrons, PP, and the polynomial hierarchy. Computational Complexity 4(4), 339–349 (1994)
Bshouty, N., Cleve, R., Gavaldà, R., Kannan, S., Tamon, C.: Oracles and queries that are sufficient for exact learning. Journal of Computer and System Sciences 52, 421–433 (1996)
Cai, J-Y.: \(S^P_2\) ⊆ ZPPNP. In Proceedings of the 42nd Annual IEEE Symposium on Foundations of Computer Science, pp. 620–629 (2001)
Fenner, S., Fortnow, L., Kurtz, S.: Gap-definable counting classes. Journal of Computer and System Sciences 48, 116–148 (1994)
Gupta, S.: Closure properties and witness reduction. Journal of Computer and System Sciences 50(3), 412–432 (1995)
Heller, H.: On relativized exponential and probabilistic complexity classes. Information and Control 71, 231–243 (1986)
Hitchcock, J.M.: The size of SPP. Theoretical Computer Science (to appear)
Klivans, A., van Melkebeek, D.: Graph nonisomorhism has subexponential size proofs unless the polynomial-time hierarchy collapses. SIAM Journal on Computing 31, 1501–1526 (2002)
Köbler, J., Schöning, U., Torán, J.: Graph isomorphism is low for PP. Journal of Computational Complexity 2, 301–330 (1992)
Ogiwara, M., Hemachandra, L.: A complexity theory of feasible closure properties. Journal of Computer and System Sciences, 295–325 (1993)
Vinodchandran, N.V.: Counting complexity of solvable group problems. SIAM Journal on Computing (2004) (to appear)
Wilson, C.B.: Reltivized circuit complexity. Journal of Computer and System Sciences 31(2), 169–181 (1985)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Vinodchandran, N.V. (2004). Learning DNFs and Circuits Using Teaching Assistants. In: Chwa, KY., Munro, J.I.J. (eds) Computing and Combinatorics. COCOON 2004. Lecture Notes in Computer Science, vol 3106. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-27798-9_22
Download citation
DOI: https://doi.org/10.1007/978-3-540-27798-9_22
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-22856-1
Online ISBN: 978-3-540-27798-9
eBook Packages: Springer Book Archive