Recent Advances and Trends in Large-Scale Kernel Methods

Hisashi KASHIMA  Tsuyoshi IDE  Tsuyoshi KATO  Masashi SUGIYAMA  

IEICE TRANSACTIONS on Information and Systems   Vol.E92-D    No.7    pp.1338-1353
Publication Date: 2009/07/01
Online ISSN: 1745-1361
DOI: 10.1587/transinf.E92.D.1338
Print ISSN: 0916-8532
Type of Manuscript: Special Section INVITED PAPER (Special Section on Large Scale Algorithms for Learning and Optimization)
kernel methods,  support vector machines,  kernel trick,  low-rank approximation,  optimization,  structured data,  

Full Text: PDF(308KB)>>
Buy this Article

Kernel methods such as the support vector machine are one of the most successful algorithms in modern machine learning. Their advantage is that linear algorithms are extended to non-linear scenarios in a straightforward way by the use of the kernel trick. However, naive use of kernel methods is computationally expensive since the computational complexity typically scales cubically with respect to the number of training samples. In this article, we review recent advances in the kernel methods, with emphasis on scalability for massive problems.

open access publishing via