Linear Convergence of a Decomposition Method for Support Vector Machines
Date Issued
2001
Date
2001
Author(s)
DOI
20060927122858289342
Abstract
Recently the asymptotic convergence of some commonly used decomposition methods for support vector machines has been established. However, their local convergence rates are still unknown. In this paper, under the assumptions that the kernel matrix is positive definite & the problem is non-degenerate, we prove the linear convergence of a popular decomposition method.
Publisher
臺北市:國立臺灣大學資訊工程學系
Type
journal article
File(s)![Thumbnail Image]()
Loading...
Name
linearconv.pdf
Size
175.57 KB
Format
Adobe PDF
Checksum
(MD5):ffd3184dbca744303a90f747eb7c2758