Estimating a Boolean Perceptron from Its Average Satisfying Assignment: A Bound on the Precision Required
A boolean perceptron is a linear threshold function over the discrete boolean domain 0, 1 n. That is, it maps any binary vector to 0 or 1 depending on whether the vector’s components satisfy some linear inequality. In 1961, Chow  showed that any boolean perceptron is determined by the average or “center of gravity” of its “true” vectors (those that are mapped to 1). Moreover, this average distinguishes the function from any other boolean function, not just other boolean perceptrons. We address an associated statisticalquestion of whether an empirical estimate of this average is likely to provide a good approximation to the perceptron. In this paper we show that an estimate that is accurate to within additive error (ε/n)O(log(1/ε)) determines a boolean perceptron that is accurate to within error ε (the fraction of misclassified vectors). This provides a mildly super-polynomial bound on the sample complexity of learning boolean perceptrons in the “restricted focus of attention” setting. In the process we also find some interesting geometrical properties of the vertices of the unit hypercube.
Unable to display preview. Download preview PDF.
- 4.S. Ben-David and E. Dichterman (1994). Learnability with restricted focus of attention guarantees noise-tolerance, 5th International Workshop on Algorithmic Learning Theory, pp. 248–259.Google Scholar
- 9.C.K. Chow (1961). On the characterization of threshold functions. Proc. Symp. on Switching Circuit Theory and Logical Design, 34–38.Google Scholar
- 10.E. Dichterman (1998). Learning with Limited Visibility. CDAM Research Reports Series, LSE-CDAM-98-01 44pp.Google Scholar
- 12.T. Eiter, T. Ibaraki and K. Makino (1998). Decision Lists and Related Boolean Functions. Institut Für Informatik JLU Giessen (IFIG) Research Reports 9804.Google Scholar
- 13.P.W. Goldberg (1999). Learning Fixed-dimension Linear Thresholds from Fragmented Data. Warwick CSdept. tech. report RR362, Sept. 99, accepted for publication in Information and Computation as of Dec. 2000. A preliminary version is in Procs of the 1999 Conference on ComputationalLearning Theory, pp. 88–99 July 1999.Google Scholar
- 15.N. Littlestone (1988). Learning Quickly When Irrelevant Attributes Abound: A New Linear-threshold Algorithm. Machine Learning 2, pp. 285–318.Google Scholar
- 16.R.L. Rivest (1996). Learning Decision Lists. Machine Learning 2 pp. 229–246.Google Scholar