Library Header Image
LSE Research Online LSE Library Services

Margin-based generalization error bounds for threshold decision lists

Anthony, Martin (2003) Margin-based generalization error bounds for threshold decision lists. CDAM research report series (LSE-CDAM-2003-09). Centre for Discrete and Applicable Mathematics, London School of Economics and Political Science, London, UK.

Full text not available from this repository.


This paper concerns the use of threshold decision lists for classifying data into two classes. The use of such methods has a natural geometrical interpretation and can be appropriate for an iterative approach to data classification, in which some points of the data set are given a particular classification, according to a linear threshold function (or hyperplane), are then removed from consideration, and the procedure iterated until all points are classified. We analyse theoretically the generalization properties of data classification techniques that are based on the use of threshold decision lists and the subclass of multilevel threshold functions. We obtain bounds on the generalization error that depend on the levels of separation — or margins —achieved by the successive linear classifiers.

Item Type: Monograph (Report)
Official URL:
Additional Information: © 2003 the author
Divisions: Mathematics
Subjects: Q Science > QA Mathematics
Date Deposited: 04 Dec 2008 14:54
Last Modified: 16 May 2024 13:07

Actions (login required)

View Item View Item