About cookies on this site Our websites require some cookies to function properly (required). In addition, other cookies may be used with your consent to analyze site usage, improve the user experience and for advertising. For more information, please review your options. By visiting our website, you agree to our processing of information as described in IBM’sprivacy statement. To provide a smooth navigation, your cookie preferences will be shared across the IBM web domains listed here.
Conference paper
Surrogate cost techniques in countable classification
Abstract
We study the problem of classification when the set of classes is a σ-compact metric space, by means of surrogate cost minimization. We give a natural sufficient condition for the optimal classifier to be of the form T f when the function f minimizes a surrogate for the actual loss defined on pairs of classes. Sequences of functions whose expectations converge to the infimum of the expectations of all such functions can then be found by minimizing the sample averages of training sets. In particular, we show how to use surrogate cost minimization when the set of classes is countable and give an example. © 2007 IEEE.