文章基本信息

标题：Multi-Objective Parameter Selection for Classifiers
本地全文：下载
作者：Christoph Müssel ; Ludwig Lausser ; Markus Maucher 等
期刊名称：Journal of Statistical Software
印刷版ISSN：1548-7660
电子版ISSN：1548-7660
出版年度：2012
卷号：46
期号：1
页码：1-27
语种：English
出版社：University of California, Los Angeles
摘要：Setting the free parameters of classifiers to different values can have a profound impact on their performance. For some methods, specialized tuning algorithms have been developed. These approaches mostly tune parameters according to a single criterion, such as the cross-validation error. However, it is sometimes desirable to obtain parameter values that optimize several concurrent - often conflicting - criteria. The TunePareto package provides a general and highly customizable framework to select optimal parameters for classifiers according to multiple objectives. Several strategies for sampling and optimizing parameters are supplied. The algorithm determines a set of Pareto-optimal parameter configurations and leaves the ultimate decision on the weighting of objectives to the researcher. Decision support is provided by novel visualization techniques.