Sparse random projection for chi(2) kernel linearization: Algorithm and applications to image classification

作者：Wang, Zhenzhen; Yuan, Xiao-Tong; Liu, Qingshan^*

来源：Neurocomputing, 2015, 151: 327-332.

DOI：10.1016/j.neucom.2014.09.032

• chi(2) Kernel
• Sparse random projection
• SVMs
• Data mining
• Image classification

The chi(2) kernel based support vector machines (SVMs) have achieved impressive performances in many image and text classification tasks. As a nonlinear kernel method, however, it does not scale well to large scale data, because the computation of the chi(2) kernel matrix is intractable. To address this challenge, we propose a sparse random projection method to linearly approximate the chi(2) kernel, so that the original nonlinear SVMs could be converted to linear ones. Then we are able to make use of the existing large scale linear SVMs training method efficiently. Experimental results on three popular image data sets (MNIST, rcv1.binary, Caltech-101) show that the proposed method can significantly improve the learning efficiency of the chi(2) kernel SVMs and the improvement comes at almost no cost of accuracy.

• 出版日期2015-3-3
• 单位南京信息工程大学