Abstract
We investigate the exact learning of real-valued functions on {0,l}n represented by a weighted sum of a number of monotone terms using queries for the values of the target function at assignments of the learner's choice. When all coefficients are nonnegative, we show that these functions are learnable with at most (n — ⌊log2 k⌋+1)k queries, where n is the number of variables and k is the number of terms in the target. We also prove a lower bound of \(\Omega \left( {\tfrac{{nk}}{{\log _2 k}}} \right)\) on the number of queries necessary for learning this class, so no algorithm can reduce the number of queries dramatically. In the general case, namely, when the coefficients vary over the reals, we show the number of queries required for exact learning of k-term subclass is upper bounded by q(n, ⌊log2 k⌋+1) and is lower bounded by q(n,⌊log2 k⌋), where \(q\left( {n,l} \right) = \sum\nolimits_{i = 0}^l {\left( {\begin{array}{*{20}c}n \\i \\\end{array} } \right)}\). The latter bounds are shown by generalizing Roth and Benedek's technique for analyzing the learning problem for k-sparse multivariate polynomials over GF(2) [8].
This is a preview of subscription content, log in via an institution.
Preview
Unable to display preview. Download preview PDF.
References
D. Angluin. Queries and concept learning. Machine Learning, 2:319–342, 1988.
D. Angluin, L. Hellerstein, and M. Karpinski. Learning read-once formulas with queries. Journal of the ACM, 40(1):185–210, January 1993.
M. Ben-Or and P. Tiwari. A Deterministic Algorithm For Sparse Multivariate Polynomial Interpolation. In Proc. of the 20th Annual ACM Symposium on Theory of Computing, pages 301–309, 1988.
Q. P. Gu and A. Maruoka. Learning Boolean Functions. Technical Report of IEICE COMP87-82, 1988.
L. Hellerstein and M. Warmuth. Interpolating GF[2] polynomials. Unpublished manuscript.
K. Kakihara and H. Imai. Notes on the PAC learning of geometric concepts with additional Information. In Proc. of Third Workshop on ALT, pages 252–259, October 1992.
F. J. MacWilliams and N. J. A. Sloane. The Theory of Error-Correcting Codes. Noth-Holland, Amsterdam, 1977.
R. M. Roth and G. M. Benedek. Interpolation and approximation of sparce multivariate polynomials over GF [2]. SIAM J. Comput., 20(2):291–314, April 1991.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1993 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Nakamura, A., Abe, N. (1993). Exact learning of linear combinations of monotone terms from function value queries. In: Jantke, K.P., Kobayashi, S., Tomita, E., Yokomori, T. (eds) Algorithmic Learning Theory. ALT 1993. Lecture Notes in Computer Science, vol 744. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-57370-4_56
Download citation
DOI: https://doi.org/10.1007/3-540-57370-4_56
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-57370-8
Online ISBN: 978-3-540-48096-9
eBook Packages: Springer Book Archive