Kramer Kurt A, Hall Lawrence O, Goldgof Dmitry B, Remsen Andrew, Luo Tong
Department of Computer Science and Engineering, University of South Florida, Tampa, FL33620-5399 USA.
IEEE Trans Syst Man Cybern B Cybern. 2009 Aug;39(4):989-1001. doi: 10.1109/TSMCB.2008.2011645. Epub 2009 Mar 24.
Support vector machines (SVMs) can be trained to be very accurate classifiers and have been used in many applications. However, the training time and, to a lesser extent, prediction time of SVMs on very large data sets can be very long. This paper presents a fast compression method to scale up SVMs to large data sets. A simple bit-reduction method is applied to reduce the cardinality of the data by weighting representative examples. We then develop SVMs trained on the weighted data. Experiments indicate that bit-reduction SVM produces a significant reduction in the time required for both training and prediction with minimum loss in accuracy. It is also shown to typically be more accurate than random sampling when the data are not overcompressed.
支持向量机（SVM）经过训练可以成为非常精确的分类器，并已在许多应用中得到使用。然而，在非常大的数据集上，支持向量机的训练时间以及在较小程度上的预测时间可能会非常长。本文提出了一种快速压缩方法，以使支持向量机能够扩展到处理大型数据集。应用一种简单的位缩减方法，通过对具有代表性的示例进行加权来减少数据的基数。然后，我们开发在加权数据上训练的支持向量机。实验表明，位缩减支持向量机在训练和预测所需时间上都有显著减少，同时准确性损失最小。当数据没有过度压缩时，它通常也比随机采样更准确。
