Abstract
We extend the notion of general dimension, a combinatorial characterization of learning complexity for arbitrary query protocols, to encompass approximate learning. This immediately yields a characterization of the learning complexity in the statistical query model. As a further application, we consider approximate learning of DNF formulas and we derive close upper and lower bounds on the number of statistical queries needed. In particular, we show that with respect to the uniform distribution, and for any constant error parameter ∈ lt; 1/2, the number of statistical queries needed to approximately learn DNF formulas (over n variables and s terms) with tolerance τ = Θ(1/s) is nΘ(log s).
Work supported by the DFG under project KO 1053/1-1
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
D. Angluin. Queries and concept learning. Machine Learning, 2:319–342, 1988.
D. Angluin. Negative results for equivalence queries. Machine Learning, 5(2):121–150, 1990.
J. Aslam and S. Decatur. General bounds on statistical query learning and PAC learning with noise via hypothesis boosting. Information and Computation, 141(2):85–118, 1998.
J. Balcázar, J. Castro, and D. Guijarro. A general dimension for exact learning. In Proc. 14th ACM Conference on Computational Learning Theory, volume 2111 of Lecture Notes in Artificial Intelligence, pages 354–367. Springer-Verlag, Berlin Heidelberg New York, 2001.
J. L. Balcázar, J. Castro, D. Guijarro, and H. U. Simon. The consistency dimension and distribution-dependent learning from queries. In Proc. 10th International Workshop on Algorithmic Learning Theory (ALT’99), Lecture Notes in Artificial Intelligence. Springer-Verlag, Berlin Heidelberg New York, 1999.
S. Ben-David, A. Itai, and E. Kushilevitz. Learning by distances. Information and Computation, pages 240–250, 1995.
A. Blum, M. Furst, J. Jackson, M. Kearns, Y. Mansour, and S. Rudich. Weakly learning DNF and characterizing statistical query learning using Fourier analysis. In ACM, editor, Proc. 26th ACM Symposium on Theory of Computing, pages 253–262. ACM Press, 1994.
A. Blumer, A. Ehrenfeucht, D. Haussler, and M. K. Warmuth. Learnability and the Vapnik-Chervonenkis dimension. Journal of the ACM, 36(4):929–965, 1989.
N. H. Bshouty and V. Feldman. On using extended statistical queries to avoid membership queries. Journal of Machine Learning Research, 2:359–395, 2002.
Y. Freund. Boosting a weak learning algorithm by majority. Information and Computation, 121(2):256–285, Sept. 1995.
T. Hegedüs. Generalized teaching dimensions and the query complexity of learning. In Proceedings of the 8th Annual Conference on Computational Learning Theory (COLT’95), pages 108–117. ACM Press, July 1995.
L. Hellerstein, K. Pillaipakkamnatt, V. Raghavan, and D. Wilkins. How many queries are needed to learn? Journal of the ACM, 43(5):840–862, 1996.
J. 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, 1997.
M. J. Kearns. Efficient noise-tolerant learning from statistical queries. Journal of the ACM, 45(6):983–1006, 1998.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2002 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Köbler, J., Lindner, W. (2002). A General Dimension for Approximately Learning Boolean Functions. In: Cesa-Bianchi, N., Numao, M., Reischuk, R. (eds) Algorithmic Learning Theory. ALT 2002. Lecture Notes in Computer Science(), vol 2533. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-36169-3_13
Download citation
DOI: https://doi.org/10.1007/3-540-36169-3_13
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-00170-6
Online ISBN: 978-3-540-36169-5
eBook Packages: Springer Book Archive