DocumentCode
2766466
Title
Convergence Proof of a Sequential Minimal Optimization Algorithm for Support Vector Regression
Author
Guo, Jun ; Takahashi, Norikazu ; Nishi, Tetsuo
Author_Institution
Kyushu Univ., Fukuoka
fYear
0
fDate
0-0 0
Firstpage
355
Lastpage
362
Abstract
A sequential minimal optimization (SMO) algorithm for support vector regression (SVR) has recently been proposed by Flake and Lawrence. However, the convergence of their algorithm has not been proved so far. In this paper, we consider an SMO algorithm, which deals with the same optimization problem as Flake and Lawrence´s SMO, and give a rigorous proof that it always stops within a finite number of iterations.
Keywords
optimisation; regression analysis; support vector machines; convergence proof; sequential minimal optimization algorithm; support vector regression; Algorithm design and analysis; Computer science; Convergence; Heuristic algorithms; Kernel; Quadratic programming; Runtime; Support vector machine classification; Support vector machines; Surges;
fLanguage
English
Publisher
ieee
Conference_Titel
Neural Networks, 2006. IJCNN '06. International Joint Conference on
Conference_Location
Vancouver, BC
Print_ISBN
0-7803-9490-9
Type
conf
DOI
10.1109/IJCNN.2006.246703
Filename
1716114
Link To Document