Abstract
In this paper we study the question how many queries are needed to “halve a given version space”. In other words: how many queries are needed to extract from the learning environment the one bit of information that rules out fifty percent of the concepts which are still candidates for the unknown target concept. We relate this problem to the classical exact learning problem. For instance, we show that lower bounds on the number of queries needed to halve a version space also apply to randomized learners (whereas the classical adversary arguments do not readily apply). Furthermore, we introduce two new combinatorial parameters, the halving dimension and the strong halving dimension, which determine the halving complexity (modulo a small constant factor) for two popular models of query learning: learning by a minimum adequate teacher (equivalence queries combined with membership queries) and learning by counterexamples (equivalence queries alone). These parameters are finally used to characterize the additional power provided by membership queries (compared to the power of equivalence queries alone). All investigations are purely information-theoretic and ignore computational issues.
Similar content being viewed by others
References
D. Angluin, Queries and concept learning, Machine Learning 2(4) (1988) 319–342.
J.L. Balcázar, J. Castro, D. Guijarro and H.U. Simon, The consistency dimension and distribution-dependent learning from queries, Theoretical Computer Science 288(2) (2002) 197–215. An extended abstract of the paper appeared in the Proceedings of ALT'99.
L. Hellerstein, K. Pillaipakkamnatt, V. Raghavan and D. Wilkins, How many queries are needed to learn? Journal of the Association on Computing Machinery 43(5) (1996) 840–862.
W. Maass, On-line with an oblivious environment and the power of randomization, in: Proceedings of the 4th Annual Workshop on Computational Learning Theory (1991) pp. 167–175.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Simon, HU. How Many Queries Are Needed to Learn One Bit of Information?. Annals of Mathematics and Artificial Intelligence 39, 333–343 (2003). https://doi.org/10.1023/A:1024601719619
Issue Date:
DOI: https://doi.org/10.1023/A:1024601719619