Inhalt des Dokuments
All Publications
| Citation key | Knebel2008 |
|---|---|
| Author | Knebel, T. and Hochreiter, S. and Obermayer, K. |
| Pages | 271 – 287 |
| Year | 2008 |
| DOI | 10.1162/neco.2008.20.1.271 |
| Journal | Neural Comput. |
| Volume | 20 |
| Number | 1 |
| Publisher | MIT Press |
| Abstract | We describe a fast Sequential Minimal Optimization (SMO) procedure for solving the dual optimization problem of the recently proposed Potential Support Vector Machine (P-SVM). The new SMO consists of a sequence of iteration steps, in which the Lagrangian is optimized either with respect to one (single SMO) or to two (dual SMO) of the Lagrange multipliers while keeping the other variables fixed. An efficient selection procedure for Lagrange multipliers is given and two heuristics for improving the SMO procedure are described: block optimization and annealing of the regularization parameter ε. A comparison between the different variants show, that the dual SMO including block optimization and annealing performs most efficient in terms of computation time. In contrast to standard Support Vector Machines (SVMs), the P-SVM is applicable to arbitrary dyadic datasets, but benchmarks are provided against libSVM's ε-SVR and C-SVC implementations for problems which are also solvable by standard SVM methods. For those problems computation time of the P-SVM is comparable or somewhat higher than the standard SVM. The number of support vectors found by the P-SVM is usually much smaller for the same generalization performance. |
| Bibtex Type of Publication | Selected:structured |
Zusatzinformationen / Extras
Quick Access:
Schnellnavigation zur Seite über Nummerneingabe