A Study on SMO-Type Decomposition Methods for Support Vector Machines

By Pai-Hsuen Chen, Rong-En Fan, Chih-Jen Lin. IEEE Transactions on Neural Networks, 2006

322 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Fast training Support Vector Machines using parallel sequential minimal optimization (2008, methodology): “Because the technique of shrinking and cache [5,8,9] is applied to SMO, one column of ( ) O lm”
Working Set Selection Using Second Order Information for Training Support Vector Machines (2005, methodology): “The following theorem explains why these two techniques are useful in practice: Fan, Chen, and Lin Theorem 5 (Finite termination and explanation of caching and shrinking techniques (Chen et al., 2006, Theorems 4 and 6)) Assume Q is positive semi-definite.”
Support Vector Machine Solvers (2007, methodology): “The quantities m(α∗), M(α∗), and yk gk(α∗) do not depend on the chosen solution (Chen et al., 2006, theorem 4).”
Improvements on Twin Support Vector Machines (2011, background): “Besides, other acceleration algorithms such as [20], [21], and the extension to semisupervised learning such as [22] are also interesting.”
QP Algorithms with Guaranteed Accuracy and Run Time for Support Vector Machines (2006, methodology): “In the next two sections we complete our run time analysis of decomposition algorithms.”