BROWSE
Detail
Conference Paper
Fixed-threshold SMO for Joint Constraint Learning Algorithm of Structural SVM
Cited 1 time in 
Download 0 time
Share 
Download 0 time
Share
- Authors
- Chang Ki Lee, Hyun Ki Kim, Myung-Gil Jang
- Issue Date
- 2008-07
- Citation
- International Conference on Research and Development in Information Retrieval 2008, pp.829-830
- Language
- English
- Type
- Conference Paper
- Project Code
- 08MS3700, Development of Web QA(Question Answering) Technology, Jang Myung Gil
- Abstract
- In this paper, we describe a fixed-threshold sequential minimal optimization (FSMO) for a joint constraint learning algorithm of structural classification SVM problems. Because FSMO uses the fact that the joint constraint formulation of structural SVM has b=0, FSMD breaks down the quadratic programming (QP) problems of structural SVM into a series of smallest QP problems, each involving only one variable. By using only one variable, FSMO is advantageous in that each QP sub-problem does not need subset selection.
- KSP Keywords
- Joint constraint, Structural SVM(SSVM), Subset selection, breaks down, constraint learning, learning algorithms, quadratic programming, sequential minimal optimization