An Error Bound Based on a Worst Likely Assignment
Eric Bax, Augusto Callejas; 9(28):859−891, 2008.
Abstract
This paper introduces a new PAC transductive error bound for classification. The method uses information from the training examples and inputs of working examples to develop a set of likely assignments to outputs of the working examples. A likely assignment with maximum error determines the bound. The method is very effective for small data sets.
[abs]
[pdf][bib]| © JMLR 2008. (edit, beta) |