Years and Authors of Summarized Original Work
1995; Hellerstein, Pilliapakkamnatt, Raghavan, Wilkins
Problem Definition
This problem concerns the query complexity of proper learning in a widely studied learning model: exact learning with membership and equivalence queries. Hellerstein et al. [10] showed that the number of (polynomially sized) queries required to learn a concept class in this model is closely related to the size of certain certificates associated with that class. This relationship gives a combinatorial characterization of the concept classes that can be learned with polynomial query complexity. Similar results were shown by Hegedüs based on the work of Moshkov [8, 13].
The Exact Learning Model
Concepts are functions f : X → { 0, 1} where X is an arbitrary domain. In exact learning, there is a hidden concept f from a known class of concepts C, and the problem is to exactly identify the concept f.
Algorithms in the exact learning model obtain information about f, the...
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Recommended Reading
Alekhnovich M, Braverman M, Feldman V, Klivans AR, Pitassi T (2004) Learnability and automatizability. In: Proceedings of the 45th annual IEEE symposium on foundations of computer science (FOCS ’04), Rome. IEEE Computer Society, Washington, DC, pp 621–630
Angluin D (1987) Queries and concept learning. Mach Learn 2(4):319–342
Angluin D (2004) Queries revisited. Theor Comput Sci 313(2):175–194
Balcan N, Hanneke S (2012) Robust interactive learning. In: Proceedings of the twenty fifth annual conference on learning theory (COLT ’12), Edinburgh, pp 20.1–20.34
Balcázar JL, Castro J, Guijarro D, Köbler J, Lindner W (2007) A general dimension for query learning. J Comput Syst Sci 73(6):924–940
Balcázar JL, Castro J, Guijarro D, Simon H-U (2002) The consistency dimension and distribution-dependent learning from queries. Theor Comput Sci 288(2):197–215
Feldman V (2006) Hardness of approximate two-level logic minimization and PAC learning with membership queries. In: Proceedings of the 38th annual ACM symposium on the theory of computing (STOC ’06), Seattle. ACM, New York, pp 363–372
Hegedüs T (1995) Generalized teaching dimensions and the query complexity of learning. In: Proceedings of the 8th annual conference on computational learning theory (COLT ’95), Santa Cruz, pp 108–117
Hellerstein L, Raghavan V (2005) Exact learning of DNF formulas using DNF hypotheses. J Comput Syst Sci 70(4):435–470
Hellerstein L, Pillaipakkamnatt K, Raghavan V, Wilkins D (1996) How many queries are needed to learn? J ACM 43(5):840–862
Hellerstein L, Kletenik D, Sellie L, Servedio R (2012) Tight bounds on proper equivalence query learning of DNF. In: Proceedings of the 25th annual conference on learning theory (COLT ’12), Edinburgh, pp 31.1—31.18
Köbler J, Lindner W (2000) Oracles in \(\Sigma ^{\text{p}}_{2}\) are sufficient for exact learning. Int J Found Comput Sci 11(4):615–632
Moshkov MY (1983) Conditional tests. Probl Kibern (in Russian) 40:131–170
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer Science+Business Media New York
About this entry
Cite this entry
Hellerstein, L. (2016). Certificate Complexity and Exact Learning. In: Kao, MY. (eds) Encyclopedia of Algorithms. Springer, New York, NY. https://doi.org/10.1007/978-1-4939-2864-4_66
Download citation
DOI: https://doi.org/10.1007/978-1-4939-2864-4_66
Published:
Publisher Name: Springer, New York, NY
Print ISBN: 978-1-4939-2863-7
Online ISBN: 978-1-4939-2864-4
eBook Packages: Computer ScienceReference Module Computer Science and Engineering