Abstract
We introduce a new combinatorial dimension that gives a good approximation of the number of queries needed to learn in the exact learning model, no matter what set of queries is used. This new dimension generalizes previous dimensions providing upper and lower bounds for all sorts of queries, and not for just example-based queries as in previous works. Our new approach gives also simpler proofs for previous results. We present specific applications of our general dimension for the case of un specified attribute value queries, and show that unspecified attribute value membership and equivalence queries are not more powerful than standard membership and equivalence queries for the problem of learning DNF formulas.
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
Dana Angluin. Queries and concept learning. Machine Learning, 2:319–342, 1988.
Dana Angluin. Negative results for equivalence queries. Machine Learning, 5: 121–150, 1990.
Jose Luis Balcázar, Jorge Castro, and David Guijarro. A new abstract combinatorial dimension of exact learning via queries. In Proc. 13th Annu. Conference on Comput. Learning Theory, pages 248–254. Morgan Kaufmann, San Francisco, 2000. Revised version to appear in JCSS.
José Luis Balcázar, Jorge Castro, David Guijarro, and Hans Ulrich Simon. The consistency dimension and distribution-dependent learning from queries. In ALT’99, volume 1720, pages 77–92. LNAI. Springer, 1999. Revised version to appear in TCS.
Andreas Birkendorf, Norbert Klasner, Christian Kuhlmann, and Hans Ulrich Simon. Structural results about exact learning with unspecified attribute values. J. of Comput. Syst. Sci., 60(2):258–277, 2000. Special Issue for COLT’ 98.
Nader H. Bshouty and David K. Wilson. On learning in the presence of unspecified attribute values. In Proc. 12th Annu. Conf. on Comput. Learning Theory, pages 81–87. ACM Press, New York, NY, 1999.
Ricard Gavaldà. On the power of equivalence queries. In Computational Learning Theory: Eurocolt’ 93, pages 193–203. Oxford University Press, 1994.
Sally Goldman and Michael Kearns. On the complexity of teaching. Journal of Computer and System Sciences, 50:20–31, 1995.
Sally A. Goldman, Stephen S. Kwek, and Stephen D. Scott. Learning from examples with unspecified attribute values. In Proc. 10th Annu. Conf. on Comput. Learning Theory, pages 231–242. ACM Press, New York, NY, 1997.
Tibor Hegedüs. Generalized teaching dimension and the query complexity of learning. In 8th Annu. Conf. on Comput. Learning Theory, pages 108–117, New York, 1995. ACM Press.
Lisa Hellerstein, Krishnan Pillaipakkamnatt, Vijay Raghavan, and Dawn Wilkins. How many queries are needed to learn? Journal of the ACM, 43(5):840–862, 1996.
Norbert Klasner and Hans Ulrich Simon. General lower bounds on the query complexity within the exact learning model. Discrete Applied Mathematics, 107:61–81, 2000.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Balcázar, J.L., Castro, J., Guijarro, D. (2001). A General Dimension for Exact Learning. In: Helmbold, D., Williamson, B. (eds) Computational Learning Theory. COLT 2001. Lecture Notes in Computer Science(), vol 2111. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-44581-1_23
Download citation
DOI: https://doi.org/10.1007/3-540-44581-1_23
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-42343-0
Online ISBN: 978-3-540-44581-4
eBook Packages: Springer Book Archive