Abstract
Decision trees are a very general computation model. Here the problem is to identify a Boolean function f out of a given set of Boolean functions F by asking for the value of f at adaptively chosen inputs. For classes F consisting of functions which may be obtained from one function g on n inputs by replacing arbitrary n−k inputs by given constants this problem is known as attribute-efficient learning with k essential attributes. Results on general classes of functions are known. More precise and often optimal results are presented for the cases where g is one of the functions disjunction, parity or threshold.
Preview
Unable to display preview. Download preview PDF.
References
Ahlswede, R. and Wegener, I. (1987). Search Problems. Wiley.
Angluin, D. (1988). Queries and concept learning. Machine Learning 2, 319–342.
Angluin, D., Hellerstein, L., and Karpinski, M. (1993). Learning read-once formulas with queries. Journal of the ACM 40, 185–210.
Bshouty, N. H. and Hellerstein, L. (1996). Attribute-efficient learning in query and mistake-bound models. Proc. of the 9th Conf. on Computational Learning Theory COLT '96, 235–243.
Friedman, J. (1984). Constructing (n log n) size monotone formulae for the k-th elementary symmetric polynomial of n Boolean variables. Proc. 25th Symp. on Foundations of Computer Science, 506–515.
Håstad, J., Wegener, I., Wurm, N., and Yi, S. (1994). Optimal depth, very small size circuits for symmetric functions in AC 0. Information and Computation 108, 200–211.
Heiman, R. and Wigderson, A. (1991). Randomized vs. deterministic decision tree complexity. Computational Complexity 1, 311–329.
Hofmeister, T. (1996). Personal communication.
Littlestone, N. (1988). Learning quickly when irrelevant attributes abound: a new linear-threshold algorithm. Machine Learning 2, 285–318.
Mehlhorn, K. (1982). On the program size of perfect and universal hash functions. Proc. 23rd Symp. on Foundations of Computer Science, 170–175.
Motwani, R. and Raghavan, P. (1995). Randomized Algorithms. Cambridge University Press.
Naor, M., Schulman, L., and Srinivasan, A. (1995). Splitters and near-optimal decomposition. Proc. 36th Symp. on Foundations of Computer Science, 182–191.
Picard, C. (1965). Théorie des Questionnaires. Gauthier-Villars, Paris.
Ragde, P. and Widgerson, A. (1991). Linear-size constant-depth polylogthreshold circuits. Information Processing Letters 39, 143–146.
Saks, M. and Widgerson, A. (1986). Probabilistic Boolean decision trees and the complexity of evaluating game trees. Proc. of 27th Symp. on Foundations of Computer Science, 29–38.
Wegener, I. (1987). The Complexity of Boolean Functions. Wiley-Teubner.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Uehara, R., Tsuchida, K., Wegener, I. (1997). Optimal attribute-efficient learning of disjunction, parity, and threshold functions. In: Ben-David, S. (eds) Computational Learning Theory. EuroCOLT 1997. Lecture Notes in Computer Science, vol 1208. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-62685-9_15
Download citation
DOI: https://doi.org/10.1007/3-540-62685-9_15
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-62685-5
Online ISBN: 978-3-540-68431-2
eBook Packages: Springer Book Archive